© 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. 113838
    Prev
    Next
    INDEX
    Explanations

    available on market

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

    contextual phrases and lists

    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
    ⌓
    0.54
     등에
    0.47
     laiss
    0.47
    िन्न
    0.46
    חש
    0.46
    ፍ
    0.46
     spannend
    0.46
     Silent
    0.45
     generazione
    0.45
     등을
    0.45
    POSITIVE LOGITS
     demographics
    0.48
     stably
    0.45
     HDL
    0.44
    et
    0.43
    ból
    0.42
    优
    0.42
    ми
    0.42
    çar
    0.42
     бата
    0.40
     കൂ
    0.40
    Activations Density 0.000%

    No Known Activations