© 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. 118996
    Prev
    Next
    INDEX
    Explanations

    return

    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
     Bajos
    -0.77
     berichtet
    -0.73
     libere
    -0.69
    μι
    -0.69
     Ново
    -0.68
     рав
    -0.68
    uramente
    -0.68
    Ɯ
    -0.67
     saliendo
    -0.67
    faq
    -0.67
    POSITIVE LOGITS
    return
    1.69
     return
    1.35
     returned
    0.87
    returnType
    0.79
     RETURN
    0.77
     Return
    0.75
     retour
    0.75
    Return
    0.75
     defenses
    0.72
    velocityX
    0.72
    Activations Density 0.018%

    No Known Activations