© 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. 2084
    Prev
    Next
    INDEX
    Explanations

    IBAction sender id

    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
    扱
    -0.82
     synd
    -0.77
     psi
    -0.71
    ToolTip
    -0.67
    cols
    -0.66
    <0xA2>
    -0.66
    数を
    -0.65
    вне
    -0.65
    ÷
    -0.64
     Lehre
    -0.64
    POSITIVE LOGITS
     vált
    0.71
     welfare
    0.68
    nergie
    0.67
     descarga
    0.64
    tenant
    0.63
     Avid
    0.61
    odos
    0.60
    SCA
    0.60
     đứng
    0.60
    るところ
    0.60
    Activations Density 0.070%

    No Known Activations