© 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. 51537
    Prev
    Next
    INDEX
    Explanations

    changing times

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

    context or assessment

    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
    nd
    0.46
    chu
    0.45
    >),
    0.44
    Efter
    0.44
    fontawesome
    0.44
    osso
    0.43
    Ce
    0.42
    }",
    0.42
    vu
    0.41
    factory
    0.41
    POSITIVE LOGITS
     KLE
    0.54
     Klan
    0.54
     لمدة
    0.48
    א
    0.47
     prawo
    0.47
    沄
    0.47
     lado
    0.46
    ležit
    0.46
     berlang
    0.46
    있는
    0.45
    Activations Density 0.000%

    No Known Activations