© 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. 128097
    Prev
    Next
    INDEX
    Explanations

    actions and relationships

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

    investing information

    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
    fiere
    0.48
    meng
    0.43
     ঘিরে
    0.43
     Biom
    0.42
     strict
    0.41
     uniaxial
    0.41
    𝒇
    0.41
    연
    0.40
     Strict
    0.39
    lier
    0.39
    POSITIVE LOGITS
     kiles
    0.48
     \,\
    0.46
     titulado
    0.46
     lask
    0.45
    ಕ್ಸ್
    0.44
     doctr
    0.43
    <unused330>
    0.42
     éto
    0.42
     đoán
    0.42
    alá
    0.41
    Activations Density 0.000%

    No Known Activations