© 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. 104365
    Prev
    Next
    INDEX
    Explanations

    commands and reports

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

    understand definitions

    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
     encarg
    0.49
     تأ
    0.46
    ﻧ
    0.42
     ون
    0.42
    の
    0.42
     resolve
    0.41
    زی
    0.41
    ဆုံး
    0.41
     मुर
    0.41
    Real
    0.41
    POSITIVE LOGITS
    oron
    0.51
     roomy
    0.48
     buono
    0.46
     disregarded
    0.46
     близь
    0.44
    揾
    0.44
    uities
    0.44
    नाची
    0.44
    ein
    0.44
    Preferred
    0.43
    Activations Density 0.001%

    No Known Activations