© 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. 219262
    Prev
    Next
    INDEX
    Explanations

    legal citations and section numbers

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

    focusing on

    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
     “
    0.52
    app
    0.50
    ↵
    0.50
    fac
    0.46
    eck
    0.46
    fak
    0.46
    lookup
    0.45
    ad
    0.45
     IK
    0.44
    plaf
    0.44
    POSITIVE LOGITS
     cursing
    0.51
     столб
    0.50
    𝐮
    0.49
     चेंजेस
    0.48
    멩
    0.48
     बोर्ड
    0.47
     sentencing
    0.47
     генера
    0.46
     कमलेश
    0.46
     sprinting
    0.46
    Activations Density 0.002%

    No Known Activations