© 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. 29146
    Prev
    Next
    INDEX
    Explanations

    urban8leadingUKweekendRegional

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

    descriptive states and processes

    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
     הד
    0.45
     ሃ
    0.44
     አ
    0.43
    }).
    0.43
    𝐋
    0.43
    같은
    0.42
    ي
    0.42
     ក
    0.42
    odigd
    0.42
     &&
    0.42
    POSITIVE LOGITS
     Comrade
    0.51
     suami
    0.50
     Harb
    0.48
     poste
    0.47
    ifelse
    0.46
     knob
    0.45
    drž
    0.45
    धव
    0.45
     mutu
    0.44
     madam
    0.43
    Activations Density 0.000%

    No Known Activations