© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69817
    Prev
    Next
    INDEX
    Explanations

    import and proposal

    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
    васто
    -0.80
     Managua
    -0.78
    Miro
    -0.78
    StartIndex
    -0.77
    Lager
    -0.77
    _));
    -0.77
    Coppa
    -0.74
     LIND
    -0.74
    CONTEN
    -0.73
    lastIndex
    -0.73
    POSITIVE LOGITS
     proposal
    1.41
     proposals
    1.35
    Proposal
    1.20
    proposal
    1.11
     Proposal
    1.07
     Proposals
    0.98
     proposing
    0.97
    POSAL
    0.93
    roi
    0.91
    proposals
    0.90
    Activations Density 0.016%

    No Known Activations