© 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. 47566
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
     those
    -1.47
     any
    -0.97
    ！(
    -0.91
    <bos>
    -0.91
    /'.$
    -0.88
     arising
    -0.85
    というわけで
    -0.85
    凝土
    -0.84
    gettime
    -0.82
    }
    -0.82
    POSITIVE LOGITS
    div
    1.13
     começo
    1.01
     implor
    0.98
     Brings
    0.95
     beset
    0.93
    ⁓
    0.93
     deleter
    0.92
     tambien
    0.91
     canadienne
    0.90
     subdiv
    0.88
    Activations Density 0.013%

    No Known Activations