© 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. 34674
    Prev
    Next
    INDEX
    Explanations

    actually two; warned; AIM market

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

    effect, cover, issue, describes, few

    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
     lateribus
    0.55
    striatis
    0.53
    methylene
    0.52
    glRaster
    0.51
     φ
    0.50
    followlike
    0.50
    Ketika
    0.50
    rvats
    0.48
    <unused25>
    0.48
     نزد
    0.48
    POSITIVE LOGITS
    ↵↵
    0.46
     prote
    0.46
     campus
    0.45
     too
    0.44
     hed
    0.44
     campuses
    0.43
     मुद्दे
    0.43
    0.42
    </i>
    0.42
     urg
    0.42
    Activations Density 0.000%

    No Known Activations