© 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. 10190
    Prev
    Next
    INDEX
    Explanations

    state, Fischer, FRITZ!, Lubbock, AIDS

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

    model responses

    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
     vattum
    0.21
     spacerItem
    0.20
     mús
    0.20
    轵
    0.20
     þat
    0.19
    rafpunkte
    0.19
    👲
    0.19
    akkhati
    0.18
    BtnFill
    0.18
     axonal
    0.18
    POSITIVE LOGITS
    c
    0.23
    d
    0.23
    e
    0.23
    p
    0.22
    k
    0.22
    l
    0.22
    2
    0.21
    to
    0.21
    up
    0.20
    g
    0.20
    Activations Density 0.127%

    No Known Activations