© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212172
    Prev
    Next
    INDEX
    Explanations

    advance beyondresearch positioncreating strongthe websiteTurning Power

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

    custom ROMs and mantras

    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
    उट
    0.47
    ্যাট
    0.45
    年的
    0.44
     理解
    0.43
     MyBatis
    0.42
    ."},
    0.41
    ⦿
    0.41
    ノ
    0.41
     referrer
    0.40
     sentir
    0.40
    POSITIVE LOGITS
     vstup
    0.50
    dies
    0.49
     amts
    0.48
     свого
    0.48
     vyroben
    0.46
    sensors
    0.46
    ुस्तान
    0.46
     inz
    0.45
    lies
    0.45
     grunn
    0.45
    Activations Density 0.001%

    No Known Activations