© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68344
    Prev
    Next
    INDEX
    Explanations

    save this page

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

    frameworks and their content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izzo
    0.51
     publicado
    0.44
    #######
    0.44
    indah
    0.44
    %%%%%%%%%%%%%%%%
    0.43
     publicación
    0.42
    aib
    0.42
     publicada
    0.42
     चित्रा
    0.42
    modelo
    0.41
    POSITIVE LOGITS
     hydrocarbons
    0.54
     fools
    0.54
     positifs
    0.49
    スン
    0.48
     수익
    0.48
     feu
    0.47
     knights
    0.47
     oxides
    0.47
    𝔱
    0.47
    스는
    0.47
    Activations Density 0.001%

    No Known Activations