© 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. 34-GEMMASCOPE-RES-131K
    7. 116463
    Prev
    Next
    INDEX
    Explanations

    from the ground up or from scratch

    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
     القد
    -0.75
    wald
    -0.72
     Theorie
    -0.72
    ács
    -0.72
    достатки
    -0.71
    گرم
    -0.71
    turns
    -0.70
     muhimu
    -0.69
    ૃ
    -0.68
     Arbeit
    -0.67
    POSITIVE LOGITS
     ground
    4.06
    ground
    2.95
    Ground
    2.78
     Ground
    2.63
    GROUND
    2.53
     GROUND
    2.39
     grounds
    1.73
     bottom
    1.57
     grounding
    1.53
    地面
    1.52
    Activations Density 0.026%

    No Known Activations