© 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. 234679
    Prev
    Next
    INDEX
    Explanations

    paid by down

    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
    ีน
    0.55
     বাল
    0.46
    ท
    0.45
     difficiles
    0.44
    ánsito
    0.43
     대회
    0.43
    erté
    0.43
    หนด
    0.43
    笳
    0.43
     Ransom
    0.42
    POSITIVE LOGITS
     proc
    0.48
     ati
    0.48
     update
    0.48
     adata
    0.47
     isn
    0.47
    a
    0.46
     atthe
    0.45
     madd
    0.45
    idx
    0.44
     aren
    0.44
    Activations Density 0.001%

    No Known Activations