© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117512
    Prev
    Next
    INDEX
    Explanations

    prefixes indicating negation or characteristics

    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_34/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
    zdroj
    -1.31
    Azi
    -1.30
    recept
    -1.23
     necessária
    -1.16
    Gön
    -1.16
    élite
    -1.15
    siamo
    -1.12
    grazie
    -1.12
    هره
    -1.10
    쐈
    -1.09
    POSITIVE LOGITS
     💀
    1.22
    era
    1.21
    ;/
    1.20
    🥴
    1.20
    😞
    1.16
     antonio
    1.16
     😂😂😂
    1.15
     paul
    1.14
    -.-
    1.14
    LAHOMA
    1.13
    Activations Density 0.320%

    No Known Activations