© 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. 58430
    Prev
    Next
    INDEX
    Explanations

    opinions and descriptions

    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
    Awesome
    -1.07
     типи
    -1.05
     Awesome
    -1.05
     team
    -1.04
    NRAS
    -1.04
    くださ
    -1.03
     лишь
    -1.02
     Indeed
    -0.99
    awesome
    -0.99
    Indeed
    -0.98
    POSITIVE LOGITS
    ᴠ
    1.24
     fucking
    1.23
     fuckin
    1.21
     droga
    1.10
     goddamn
    1.04
     motherfucker
    1.00
     furia
    0.99
    fucking
    0.98
    nft
    0.98
     laba
    0.97
    Activations Density 0.039%

    No Known Activations