© 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. 115484
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
     cél
    -0.71
    iej
    -0.70
     McDermott
    -0.68
    principalColumn
    -0.68
    nessed
    -0.66
     Rücken
    -0.66
     directo
    -0.66
    BERG
    -0.66
     ложки
    -0.65
    hebt
    -0.64
    POSITIVE LOGITS
     Bern
    0.75
     Gode
    0.73
    PKCS
    0.70
     MAF
    0.69
     thừa
    0.69
     Hil
    0.67
     dex
    0.66
     Jad
    0.66
     Carlo
    0.65
    च्छ
    0.65
    Activations Density 0.072%

    No Known Activations