© 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. 121711
    Prev
    Next
    INDEX
    Explanations

    money and prices

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

    delicate balance, isolate the, beginning the

    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
    i
    0.59
     It
    0.51
    ocation
    0.50
    ching
    0.50
    Ｕ
    0.46
     The
    0.44
    iant
    0.44
    त
    0.44
    ind
    0.43
    ран
    0.43
    POSITIVE LOGITS
     olhos
    0.59
     atuação
    0.58
     solução
    0.53
     soluzione
    0.52
     vestido
    0.51
     transformação
    0.51
     transparente
    0.51
     Fórmula
    0.50
     músicos
    0.50
     produção
    0.50
    Activations Density 0.001%

    No Known Activations