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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66989
    Prev
    Next
    INDEX
    Explanations

    Preradiosurgical embolization

    np_acts-logits-general · gemini-2.5-flash-lite

    underscore characters in programming code and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     sés
    -1.34
     jugo
    -1.26
     dieną
    -1.20
    МС
    -1.18
     transparentes
    -1.18
     polé
    -1.18
    plakat
    -1.18
    jeje
    -1.13
     språk
    -1.13
     emblema
    -1.13
    POSITIVE LOGITS
    V
    1.57
    K
    1.45
    T
    1.44
    C
    1.42
    A
    1.42
    H
    1.41
    P
    1.38
    F
    1.37
    E
    1.36
    ori
    1.30
    Activations Density 0.000%

    No Known Activations