© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12202
    Prev
    Next
    INDEX
    Explanations

    finding elements and ranges

    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
     each
    -1.25
    至
    -1.21
     both
    -1.20
    王
    -1.11
    另一
    -1.09
    ícias
    -1.09
    增加
    -1.06
    keren
    -1.05
    是否
    -1.05
     kredit
    -1.04
    POSITIVE LOGITS
     suivie
    1.24
    افی
    1.19
     semblable
    1.18
     normaux
    1.15
    grazie
    1.14
    zelfde
    1.10
     tampoco
    1.09
     nommée
    1.09
    posicao
    1.09
    blouse
    1.08
    Activations Density 0.001%

    No Known Activations