© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72058
    Prev
    Next
    INDEX
    Explanations

    Grandma, Grandpa, Harold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    焄
    -3.00
     使っ
    -2.81
    เพราะ
    -2.73
    缡
    -2.73
    anyahu
    -2.73
    辚
    -2.70
    ญี่ป
    -2.67
    翾
    -2.66
    
    -2.64
    銫
    -2.61
    POSITIVE LOGITS
    y
    3.88
    C
    3.59
    O
    3.33
    he
    3.27
    F
    3.16
    It
    3.08
    j
    3.06
    OS
    2.98
    D
    2.97
    —
    2.88
    Activations Density 0.003%

    No Known Activations