© 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. 8935
    Prev
    Next
    INDEX
    Explanations

    two-thirds

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

    mathematical or technical terms followed by punctuation/context

    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
     Hidden
    0.51
    }")
    0.48
     peck
    0.47
     viciss
    0.46
    Ре
    0.45
     pathways
    0.45
     weakly
    0.45
     ré
    0.45
     greed
    0.44
     hidden
    0.44
    POSITIVE LOGITS
     販売
    0.52
     LENGTH
    0.50
    radiol
    0.48
     BlogPost
    0.47
     প্রয়োজন
    0.47
     বয়স
    0.46
    ｕ
    0.45
    טר
    0.45
    toNumber
    0.44
    就不
    0.43
    Activations Density 0.000%

    No Known Activations