© 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. 8964
    Prev
    Next
    INDEX
    Explanations

    geographical locations or affiliations

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

    descriptive terms and specifics

    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
     ########.
    0.34
     Variablen
    0.32
     ausreichend
    0.31
     regione
    0.30
    啍
    0.30
    ↵
    0.29
    }\\
    0.29
    siehe
    0.29
     sullen
    0.29
    വിധ
    0.29
    POSITIVE LOGITS
    様専用
    0.37
    ong
    0.31
    ing
    0.29
    POA
    0.29
    ub
    0.29
    ap
    0.29
    _
    0.29
    লি
    0.28
    льные
    0.28
    జ్
    0.28
    Activations Density 0.286%

    No Known Activations