© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57568
    Prev
    Next
    INDEX
    Explanations

    names after Roger

    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
     〈
    -0.80
     Repetition
    -0.78
     pathos
    -0.77
    在我的
    -0.77
    ゼロ
    -0.77
    ブランド
    -0.77
    integers
    -0.76
    ό
    -0.73
     उन्हें
    -0.73
    icator
    -0.72
    POSITIVE LOGITS
     Rogers
    0.84
     Insight
    0.73
     cognitive
    0.72
    вный
    0.72
     through
    0.71
     испол
    0.70
    Rogers
    0.69
     Princip
    0.68
     Botanical
    0.68
     vegetable
    0.67
    Activations Density 0.026%

    No Known Activations