© 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. 66060
    Prev
    Next
    INDEX
    Explanations

    legal obligations and rights

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

    wondered why

    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
    o
    0.55
    oire
    0.51
     —
    0.51
    “.
    0.51
    Search
    0.49
    erald
    0.49
    oes
    0.48
    `.
    0.48
    rz
    0.47
    ibre
    0.47
    POSITIVE LOGITS
    事
    0.53
    扞
    0.52
     quede
    0.52
     ricordo
    0.50
     elenc
    0.50
     liczba
    0.49
     agreg
    0.49
     njima
    0.49
     entrega
    0.48
     devad
    0.48
    Activations Density 0.000%

    No Known Activations