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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7333
    Prev
    Next
    INDEX
    Explanations

    cold concepts and contexts

    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
    сси
    -0.81
    mister
    -0.81
    bánh
    -0.77
    distrito
    -0.77
     known
    -0.74
     نمونه
    -0.73
     raisins
    -0.73
     информацию
    -0.73
     spanned
    -0.72
    bols
    -0.71
    POSITIVE LOGITS
     cold
    2.25
    cold
    2.16
     Cold
    1.98
    Cold
    1.97
     COLD
    1.82
    blooded
    1.65
    COLD
    1.52
    🥶
    1.26
    冷
    1.21
     hearted
    1.17
    Activations Density 0.014%

    No Known Activations