© 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. 51426
    Prev
    Next
    INDEX
    Explanations

    carry all

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

    asking about factors

    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
    to
    0.51
    ハマ
    0.50
    お
    0.49
    archives
    0.48
    jms
    0.48
    esm
    0.47
    tau
    0.46
    toj
    0.46
    ご
    0.46
    implies
    0.46
    POSITIVE LOGITS
     citrate
    0.52
    వైపు
    0.49
     ángulo
    0.46
     centrale
    0.46
     sulphate
    0.46
     centrally
    0.45
     soluciones
    0.44
     fout
    0.43
     retorted
    0.43
     desorption
    0.42
    Activations Density 0.000%

    No Known Activations