© 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. 58000
    Prev
    Next
    INDEX
    Explanations

    credit cards

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

    llama ears like bananas

    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
    Windows
    0.59
    WAY
    0.53
    ST
    0.51
    VOLUME
    0.50
    Y
    0.49
    YEAR
    0.49
    Year
    0.47
    6
    0.47
    Ave
    0.46
    5
    0.46
    POSITIVE LOGITS
    ِب
    0.47
    Ⴉ
    0.47
    肿
    0.46
    ষ্ঠান
    0.43
     particuliers
    0.43
    boolProp
    0.42
     каким
    0.42
    roly
    0.42
    henol
    0.41
    leti
    0.41
    Activations Density 0.000%

    No Known Activations