© 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. 22-GEMMASCOPE-RES-131K
    7. 70753
    Prev
    Next
    INDEX
    Explanations

    treated as

    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_22/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
     harmless
    -1.11
    いれば
    -1.02
     successivo
    -1.01
     satisfactory
    -0.98
     remission
    -0.91
     properly
    -0.88
    Investi
    -0.84
    お試し
    -0.83
    そこまで
    -0.81
     presumably
    -0.81
    POSITIVE LOGITS
     unfavorable
    1.13
     worse
    1.07
     unfavourable
    0.99
    ЖА
    0.91
     worsen
    0.91
    ternut
    0.90
    glDelete
    0.90
     rossz
    0.90
    ares
    0.89
     wors
    0.89
    Activations Density 0.186%

    No Known Activations