© 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. 135942
    Prev
    Next
    INDEX
    Explanations

    article orauthor'smother andnow.skills.you analyze

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

    meaning and purposes

    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
    Radi
    0.50
     Radi
    0.50
    nity
    0.47
    ।
    0.47
    莫名
    0.46
    garbage
    0.45
     Refining
    0.45
     ڈیٹا
    0.45
    RADI
    0.44
    ceiver
    0.44
    POSITIVE LOGITS
     buys
    0.55
    ър
    0.52
     chained
    0.52
     attend
    0.52
     attends
    0.51
    ත්‍
    0.51
     swoop
    0.50
     collaborates
    0.49
     agron
    0.48
    ъ
    0.47
    Activations Density 0.000%

    No Known Activations