© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 89
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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_16k_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
     (^
    1.58
     (=
    1.54
     totals
    1.50
     rather
    1.47
     Probability
    1.47
     (~
    1.44
     (‘
    1.43
     only
    1.42
     grams
    1.42
     ONLY
    1.41
    POSITIVE LOGITS
    крытие
    1.02
    ```
    0.99
    цем
    0.97
    import
    0.95
    久
    0.92
    كام
    0.91
     проходи
    0.90
    ця
    0.88
     структуру
    0.85
    يطان
    0.85
    Activations Density 2.323%

    No Known Activations