© 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. 93269
    Prev
    Next
    INDEX
    Explanations

    programmatic 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_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
    鲎
    -1.13
     verschied
    -1.12
    served
    -1.09
    苺
    -1.06
    commissioned
    -1.06
     ähnliche
    -1.03
    销毁
    -1.02
    噠
    -1.02
     derselben
    -1.01
     قام
    -1.01
    POSITIVE LOGITS
     their
    1.44
     our
    1.35
     bolso
    1.13
    ğını
    1.13
    猻
    1.11
     defekt
    1.10
    ״
    1.09
     hadas
    1.08
     all
    1.06
    İş
    1.03
    Activations Density 0.005%

    No Known Activations