© 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. 57855
    Prev
    Next
    INDEX
    Explanations

    aluminium frame

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

    internal conflict and consequences

    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
    হো
    0.58
    ходил
    0.54
     એપ
    0.53
    сово
    0.52
     gră
    0.51
    dı
    0.50
     ⿱
    0.49
    ને
    0.49
     находи
    0.49
     înviat
    0.49
    POSITIVE LOGITS
    ANN
    0.44
     jurisprudence
    0.44
    Larry
    0.42
    lager
    0.42
    Thanks
    0.42
     ethics
    0.42
    unless
    0.41
     Hawk
    0.41
     Unterstützung
    0.41
     Gesundheit
    0.41
    Activations Density 0.000%

    No Known Activations