© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3090
    Prev
    Next
    INDEX
    Explanations

    HTML form.html string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     速
    1.85
     hội
    1.67
    RowFilter
    1.64
    ᱥ
    1.62
     fhe
    1.61
     calendário
    1.60
    сле
    1.58
    딧
    1.57
    граммы
    1.55
    𝗸
    1.53
    POSITIVE LOGITS
    .
    6.50
    。
    5.64
    ।
    4.97
    !
    4.66
    .]
    4.58
    ;
    4.54
    !.
    4.53
    ].
    4.46
    ).
    4.33
    .}
    4.21
    Activations Density 0.642%

    No Known Activations