© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4259
    Prev
    Next
    INDEX
    Explanations

    dialogue scene setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     ramo
    1.49
    stash
    1.49
    véd
    1.45
    กก
    1.41
    褸
    1.41
    ススメ
    1.40
     Mimpi
    1.38
     시리즈
    1.37
    类别
    1.35
    aš
    1.35
    POSITIVE LOGITS
    olate
    1.71
    "];
    1.52
    gerufen
    1.52
    .],
    1.50
     ↑
    1.49
     [
    1.48
    人在
    1.44
    ].
    1.43
    ades
    1.40
    ],
    1.39
    Activations Density 0.041%

    No Known Activations