© 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. 101429
    Prev
    Next
    INDEX
    Explanations

    years or

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

    without explicit consent

    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
    인의
    0.48
    인을
    0.45
     jõ
    0.45
    ኒ
    0.42
     apna
    0.42
     stark
    0.41
    ressive
    0.40
    crackers
    0.40
    尽
    0.39
     replete
    0.39
    POSITIVE LOGITS
    CodeGen
    0.51
     mungkin
    0.50
    ક્તિ
    0.49
     Actual
    0.47
     তাহাদিগকে
    0.47
    Actual
    0.45
    ঙ্কর
    0.45
     kanske
    0.45
    combined
    0.45
    notation
    0.44
    Activations Density 0.001%

    No Known Activations