© 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. 42871
    Prev
    Next
    INDEX
    Explanations

    business plans

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

    quite versatile

    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
    телем
    0.54
    ocamp
    0.49
     Pentec
    0.46
     γίνεται
    0.45
    яви
    0.44
     fiasco
    0.43
    писание
    0.43
    ा
    0.43
     palpable
    0.42
    दिया
    0.42
    POSITIVE LOGITS
    サーバー
    0.50
    內
    0.46
    ihn
    0.43
    รัฐ
    0.43
    rade
    0.43
     uncover
    0.42
    rable
    0.41
    aremos
    0.39
    内に
    0.39
    assan
    0.39
    Activations Density 0.000%

    No Known Activations