© 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. 173730
    Prev
    Next
    INDEX
    Explanations

    pot calls the kettle black

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

    describing possibilities or next steps

    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
    锼
    0.49
    ڄ
    0.47
    між
    0.46
     nih
    0.45
    镓
    0.45
    锑
    0.45
    埝
    0.44
     $\%$
    0.44
    தேசம்
    0.44
    ╽
    0.44
    POSITIVE LOGITS
    "
    0.53
    ous
    0.49
    otr
    0.47
    tr
    0.47
    1
    0.47
    a
    0.46
    ac
    0.46
    at
    0.45
    ak
    0.45
     bac
    0.45
    Activations Density 0.000%

    No Known Activations