© 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. 208937
    Prev
    Next
    INDEX
    Explanations

    . attack. target

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

    active development

    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
     overr
    0.52
     ugu
    0.51
    जीर
    0.48
     received
    0.47
     celeb
    0.47
     meditate
    0.46
     horoscope
    0.46
    🏘
    0.45
     probs
    0.45
     ora
    0.44
    POSITIVE LOGITS
    ндар
    0.50
    ляция
    0.47
     Eastman
    0.45
    шы
    0.44
    h
    0.43
    рован
    0.43
     Nutzen
    0.43
    ды
    0.42
     Silverman
    0.41
    ভূতির
    0.41
    Activations Density 0.000%

    No Known Activations