© 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. 57325
    Prev
    Next
    INDEX
    Explanations

    input type="text"

    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
     Jinping
    -0.77
    甫
    -0.73
    必需
    -0.70
     تازه
    -0.69
    そのため
    -0.69
    umal
    -0.69
     AttributeSet
    -0.68
     לכ
    -0.68
     pays
    -0.68
     Lay
    -0.67
    POSITIVE LOGITS
     текста
    0.88
    email
    0.85
    莽
    0.85
     оригинала
    0.84
    submit
    0.82
     unknownFields
    0.78
     compañía
    0.76
    number
    0.75
    mación
    0.75
     rzeczyw
    0.75
    Activations Density 0.006%

    No Known Activations