© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11229
    Prev
    Next
    INDEX
    Explanations

    mathematical geometrical parameter

    np_acts-logits-general · gemini-2.5-flash-lite

    structural cues that mark the start of an assistant response or a new section, such as headings, numbered list entries, or formatting delimiters.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    The
    0.46
    这是一
    0.37
     პ
    0.35
    सी
    0.34
    Our
    0.34
     नई
    0.34
     Университе
    0.34
     Öncelikle
    0.34
     πρώτη
    0.34
     Detalles
    0.34
    POSITIVE LOGITS
     parameter
    0.46
     powders
    0.45
     matrix
    0.44
     geometrical
    0.43
     tiles
    0.43
     fermion
    0.43
     aggregates
    0.42
     blobs
    0.42
     flux
    0.41
     kernels
    0.41
    Activations Density 0.141%

    No Known Activations