© 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. 11296
    Prev
    Next
    INDEX
    Explanations

    states of being

    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
    5
    -1.31
    を
    -1.27
    しかし
    -1.27
    了一
    -1.22
    6
    -1.20
    8
    -1.18
     =
    -1.13
    3
    -1.11
    7
    -1.11
    gá
    -1.10
    POSITIVE LOGITS
    armani
    1.26
     or
    1.21
     some
    1.19
    consejos
    1.11
     any
    1.11
     high
    1.09
     など
    1.07
     either
    1.06
    cómo
    1.06
     changed
    1.05
    Activations Density 0.062%

    No Known Activations