© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208356
    Prev
    Next
    INDEX
    Explanations

    trailer deck

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

    computer data types and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    0.61
    ان
    0.53
     大阪
    0.51
    𝟰
    0.50
     Complexity
    0.49
    analysis
    0.49
     Always
    0.48
    燭
    0.48
    analyses
    0.48
    electrons
    0.47
    POSITIVE LOGITS
    ץ
    0.45
    łącznie
    0.44
     entorno
    0.43
    캥
    0.43
    ιου
    0.43
    ί
    0.42
     $+
    0.42
    ﻪ
    0.42
    었는데
    0.41
    що
    0.41
    Activations Density 0.000%

    No Known Activations