© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2662
    Prev
    Next
    INDEX
    Explanations

    comes from

    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_16_width_65k_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
    ва
    0.66
    е
    0.64
    ре
    0.63
    ED
    0.63
    ان
    0.59
    an
    0.58
    то
    0.58
    ه
    0.56
    ка
    0.55
    IS
    0.55
    POSITIVE LOGITS
    ுகிற
    0.46
     hijack
    0.45
     blackout
    0.44
    </h6>
    0.41
     thunderstorm
    0.41
     boarded
    0.41
     Recession
    0.41
     proactive
    0.40
     is
    0.40
    ДА
    0.40
    Activations Density 0.290%

    No Known Activations