© 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. 61164
    Prev
    Next
    INDEX
    Explanations

    controller classes

    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
    ジナル
    0.43
    cardNumber
    0.42
    框
    0.42
    ο
    0.41
    тики
    0.40
    テク
    0.39
     ENTRE
    0.39
    オ
    0.39
     알
    0.39
     тек
    0.39
    POSITIVE LOGITS
    Rourke
    0.47
     Rishi
    0.43
    Aid
    0.43
    Set
    0.42
    Sensitive
    0.42
     Rai
    0.42
    preprocess
    0.41
    Cit
    0.41
    rocytes
    0.41
    Cone
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.