© 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. 163097
    Prev
    Next
    INDEX
    Explanations

    limit, sponsor, events, year

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

    concatenating code examples

    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
     be
    0.47
    є
    0.46
    ү
    0.45
    يا
    0.44
    чо
    0.42
    stück
    0.42
    蔽
    0.42
    ها
    0.42
    तो
    0.41
    語
    0.41
    POSITIVE LOGITS
     উক্ত
    0.54
     बढ़ने
    0.49
     قریب
    0.49
     한다는
    0.49
     சிறு
    0.48
    irma
    0.48
     একটু
    0.47
     부터
    0.47
    isil
    0.46
     JSTOR
    0.46
    Activations Density 0.000%

    No Known Activations