© 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. 60323
    Prev
    Next
    INDEX
    Explanations

    homes have

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

    AI can't replace judgment

    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
    alt
    0.47
    jm
    0.47
    lv
    0.46
    signature
    0.45
    g
    0.45
    d
    0.45
    .".
    0.44
    se
    0.44
    bdm
    0.43
    jsr
    0.43
    POSITIVE LOGITS
     勺
    0.54
    是为了
    0.53
    NEE
    0.53
     assurent
    0.52
     உள்ள
    0.52
    はその
    0.52
     아니다
    0.52
    NEA
    0.49
     ندار
    0.48
     탱크
    0.48
    Activations Density 0.000%

    No Known Activations