© 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. 22-GEMMASCOPE-RES-131K
    7. 12156
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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_22/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
    ༼
    -1.30
    grafik
    -1.27
     ſal
    -1.22
    修为
    -1.18
     FISCAL
    -1.16
    savevideo
    -1.16
    dailymail
    -1.15
    voyage
    -1.14
    batman
    -1.13
     FEBRUARY
    -1.13
    POSITIVE LOGITS
     ہیں
    1.27
     Eigentum
    1.21
    varphi
    1.20
    1
    1.05
    3
    1.04
    Da
    1.04
     m
    1.03
    6
    1.02
    ༌
    1.02
    orm
    1.01
    Activations Density 0.048%

    No Known Activations