© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 563
    Prev
    Next
    INDEX
    Explanations

    sample files or registration events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kona
    0.42
     henkil
    0.42
    狛
    0.41
     laik
    0.41
    ܪ
    0.41
    ………….
    0.41
    ěr
    0.41
     hôtels
    0.40
    ž
    0.39
    魍
    0.39
    POSITIVE LOGITS
    DF
    0.57
     F
    0.55
     FF
    0.50
     DF
    0.47
    FP
    0.42
     MF
    0.42
    ન્
    0.41
     FT
    0.41
     rapidly
    0.41
    MF
    0.41
    Activations Density 0.176%

    No Known Activations