© 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. 105618
    Prev
    Next
    INDEX
    Explanations

    to keep

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

    progress, time, or outcomes

    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
    illum
    0.46
     అభిమా
    0.42
     (
    0.41
    my
    0.41
    helicopter
    0.41
    wall
    0.40
    である
    0.40
    qe
    0.40
    jpg
    0.40
    lam
    0.40
    POSITIVE LOGITS
     zwycię
    0.44
    ęk
    0.44
    뱉
    0.44
    MESSAGE
    0.43
    ட்டர்
    0.42
    आईएस
    0.41
    赢
    0.41
     دروس
    0.41
    Senha
    0.40
     diferença
    0.40
    Activations Density 0.005%

    No Known Activations