© 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. 172239
    Prev
    Next
    INDEX
    Explanations

    homeowners insurance or business call

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

    foreign language or special characters

    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
    qual
    0.43
     contrato
    0.43
    اقه
    0.42
     gard
    0.42
    </em>
    0.42
    graph
    0.42
    aop
    0.40
    ávan
    0.40
     tú
    0.40
    개의
    0.40
    POSITIVE LOGITS
    〠
    0.46
    μπο
    0.43
    ーリー
    0.42
     ประมาณ
    0.41
     주로
    0.41
    Answer
    0.41
    名は
    0.40
     यानी
    0.40
    を中心
    0.40
     unsuspecting
    0.40
    Activations Density 0.000%

    No Known Activations