© 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. 55529
    Prev
    Next
    INDEX
    Explanations

    mentioned in attempts

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

    lists, conjunctions, and specific qualifiers

    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
    ת
    0.41
    У
    0.38
    Luego
    0.38
     ardından
    0.37
    נ
    0.37
    בי
    0.37
    อ
    0.36
    ਾ
    0.36
    В
    0.35
    Де
    0.35
    POSITIVE LOGITS
     அடிக்கடி
    0.35
     πιο
    0.34
     সত্যিই
    0.34
    几次
    0.34
    CString
    0.31
     சிலையை
    0.31
     sırasında
    0.30
     opravdu
    0.30
     regenv
    0.30
     নামটি
    0.29
    Activations Density 0.093%

    No Known Activations