© 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. 136287
    Prev
    Next
    INDEX
    Explanations

    deity, comfortable, victims, reflect, Fox, relax, ontology

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

    slot filling

    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
    ,
    0.51
    कर
    0.46
    ified
    0.46
    ランプ
    0.46
     Parole
    0.46
    ification
    0.45
     epoxy
    0.44
     kari
    0.44
     Epoxy
    0.43
    Dec
    0.43
    POSITIVE LOGITS
    ął
    0.55
     belast
    0.48
    aqs
    0.47
    ྷ
    0.47
    islava
    0.45
    orial
    0.43
     میکرز
    0.42
    urndata
    0.42
    éna
    0.42
     اكبر
    0.42
    Activations Density 0.000%

    No Known Activations