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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38296
    Prev
    Next
    INDEX
    Explanations

    Template, value, or code fragments

    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
     всіх
    -0.96
    owskiego
    -0.95
    יבור
    -0.95
    كامل
    -0.94
     kaikki
    -0.94
    roth
    -0.93
    BDL
    -0.91
    ፌ
    -0.90
    一條
    -0.89
     усі
    -0.88
    POSITIVE LOGITS
     that
    1.05
    )²
    1.02
    ʹ
    0.89
    izator
    0.89
     tegens
    0.89
    acters
    0.86
     from
    0.85
     their
    0.85
    fillment
    0.84
    Blanc
    0.84
    Activations Density 0.009%

    No Known Activations