© 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-262K
    7. 117707
    Prev
    Next
    INDEX
    Explanations

    Johan Liebert witches trick

    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_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
    $
    0.69
    1
    0.64
    HAN
    0.55
    5
    0.50
    AD
    0.48
    ennie
    0.45
     i
    0.45
    oun
    0.45
    藍
    0.45
    HN
    0.44
    POSITIVE LOGITS
    deleteOne
    0.54
    蚌
    0.51
    ч
    0.50
     직접
    0.49
     ఉత్ప
    0.48
     PDEs
    0.48
    醐
    0.48
    волю
    0.48
     Gul
    0.48
    ქვს
    0.48
    Activations Density 0.000%

    No Known Activations