© 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. 49199
    Prev
    Next
    INDEX
    Explanations

    LayerMask ground, collision, dash

    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
     সমাবেশ
    0.54
     vọng
    0.51
    u
    0.50
     Wildlife
    0.47
     числе
    0.47
    MOVEMENT
    0.46
     সমাবেশে
    0.46
     சமய
    0.46
    orne
    0.46
     }}$.
    0.46
    POSITIVE LOGITS
     raises
    0.54
    ಡ್
    0.54
    र्जर
    0.53
    রা
    0.53
    ็ต
    0.52
    ňuje
    0.52
     vollständig
    0.52
    고
    0.52
     Ев
    0.52
    ńczy
    0.52
    Activations Density 0.000%

    No Known Activations