© 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. 90871
    Prev
    Next
    INDEX
    Explanations

    form group

    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
    ௅
    -0.86
     всички
    -0.85
    ğını
    -0.85
     Tilt
    -0.85
    ロシア
    -0.84
    　『
    -0.84
     Belén
    -0.83
    若い
    -0.83
    viale
    -0.82
    每个
    -0.81
    POSITIVE LOGITS
     group
    1.24
    group
    1.09
     gruppo
    1.01
     grupo
    0.99
    groupName
    0.96
    FormGroup
    0.94
     Group
    0.94
    Group
    0.90
    GROUP
    0.88
    gruppe
    0.88
    Activations Density 0.001%

    No Known Activations