© 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. 11495
    Prev
    Next
    INDEX
    Explanations

    End, Skin, A tokens then specific words

    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
     statut
    -1.27
     ſou
    -1.23
     Teknik
    -1.20
     universite
    -1.17
     gada
    -1.16
     metode
    -1.16
    canActivate
    -1.15
     teolog
    -1.13
     parlament
    -1.11
     chevalier
    -1.11
    POSITIVE LOGITS
    w
    1.26
    For
    1.13
    for
    1.13
    u
    1.13
    _
    1.11
    c
    1.10
    f
    1.09
     added
    1.08
    re
    1.05
     updated
    1.05
    Activations Density 0.000%

    No Known Activations