© 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. 79056
    Prev
    Next
    INDEX
    Explanations

    constructive, study, unit, essential, sequence

    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
    Upstream
    -0.81
     thursday
    -0.79
    pectives
    -0.77
    Datas
    -0.75
     forskellige
    -0.75
     Sonos
    -0.74
    リュ
    -0.73
    疲
    -0.73
    RadioGroup
    -0.72
     Strengths
    -0.72
    POSITIVE LOGITS
    strand
    0.97
     essential
    0.92
     SEQUENCE
    0.80
    essential
    0.79
    oward
    0.79
    bigg
    0.78
    sequence
    0.78
     benchmark
    0.77
    sequ
    0.76
    goire
    0.76
    Activations Density 0.018%

    No Known Activations