© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23245
    Prev
    Next
    INDEX
    Explanations

    RGB values, categories, states, letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    脍
    0.51
     везе
    0.42
    膾
    0.42
     ká
    0.41
     beragam
    0.39
     แถม
    0.39
     คน
    0.39
    绅
    0.39
     تضم
    0.38
    书法
    0.38
    POSITIVE LOGITS
     ($\
    0.45
     (=
    0.43
     tuple
    0.42
     reorganized
    0.42
    cc
    0.41
    seq
    0.41
     reversed
    0.41
     invariants
    0.40
    (=
    0.40
     groupby
    0.40
    Activations Density 0.046%

    No Known Activations