© 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. 189451
    Prev
    Next
    INDEX
    Explanations

    celebrated, vehicle, enabled, hut, venue

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

    muffled speech outputs

    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
    p
    0.47
    </code>
    0.45
     دھو
    0.45
    transforms
    0.45
    哑
    0.45
    d
    0.43
    i
    0.43
    emph
    0.41
    ದುಕೊಳ್ಳ
    0.41
    dense
    0.41
    POSITIVE LOGITS
     Víctor
    0.46
     IUnary
    0.45
    菄
    0.45
     soient
    0.45
    आर
    0.44
     पंजा
    0.43
     tarefa
    0.43
     Fáb
    0.42
     പി
    0.42
    riente
    0.42
    Activations Density 0.001%

    No Known Activations