© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115530
    Prev
    Next
    INDEX
    Explanations

    bass and frequencies

    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
    abolic
    -0.71
    bone
    -0.69
     Capsule
    -0.66
     archipelago
    -0.65
     panahon
    -0.64
    AID
    -0.64
    business
    -0.64
     Bedrock
    -0.63
    Mid
    -0.62
    ジア
    -0.62
    POSITIVE LOGITS
     bass
    2.84
     Bass
    2.27
    bass
    2.19
    Bass
    2.14
     basses
    1.81
     BASS
    1.80
     basse
    1.75
    BASS
    1.61
     bassist
    1.59
    低
    1.41
    Activations Density 0.041%

    No Known Activations