© 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. 107050
    Prev
    Next
    INDEX
    Explanations

    comfortable descriptions

    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
     or
    -1.08
     from
    -1.02
    itic
    -0.97
    umers
    -0.95
     NULL
    -0.92
    peech
    -0.91
    ERVER
    -0.88
    sourceType
    -0.86
    rawn
    -0.84
    panes
    -0.84
    POSITIVE LOGITS
     adequate
    1.30
     spacious
    1.20
     adequately
    1.16
    Ours
    1.13
     amply
    1.12
     equip
    1.05
     comfortable
    1.02
     equipping
    1.01
    óval
    1.00
     overlooked
    1.00
    Activations Density 0.005%

    No Known Activations