© 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. 10-GEMMASCOPE-RES-131K
    7. 104851
    Prev
    Next
    INDEX
    Explanations

    because of this

    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_10/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
    турой
    -1.58
    暸
    -1.53
    }$
    -1.49
    ieuses
    -1.42
     now
    -1.37
     to
    -1.36
    著名的
    -1.35
    ispiele
    -1.34
    彼女は
    -1.34
    ⎚
    -1.34
    POSITIVE LOGITS
    蕺
    1.63
    ooooo
    1.60
     vermag
    1.59
    oooooo
    1.55
     verhind
    1.51
    oooo
    1.45
    ଢ
    1.44
    ooooooo
    1.41
    selbe
    1.40
    employees
    1.38
    Activations Density 0.009%

    No Known Activations