© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109840
    Prev
    Next
    INDEX
    Explanations

    words starting with sher

    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_34/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
     clearly
    -0.82
    SARS
    -0.76
     verbessern
    -0.75
     Delicious
    -0.75
     SARS
    -0.74
    <u>
    -0.73
    Switching
    -0.73
     Clearly
    -0.72
    ebra
    -0.72
     Prayer
    -0.72
    POSITIVE LOGITS
     sher
    0.76
     नव
    0.75
    Cheque
    0.74
     #:
    0.74
     ラウンド
    0.73
     injunction
    0.71
     Polka
    0.70
     massif
    0.70
     SHER
    0.70
    Bata
    0.68
    Activations Density 0.010%

    No Known Activations