© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1800
    Prev
    Next
    INDEX
    Explanations

    LLaMA, bKash, Lysandra, mallard, GlobalProtect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
     minifyEnabled
    0.85
    与此同时
    0.82
    ième
    0.81
    ل
    0.81
     convened
    0.80
    毫米
    0.78
    ሎጂ
    0.78
     quantitatively
    0.74
     instituted
    0.73
    ﻝ
    0.73
    POSITIVE LOGITS
     unui
    0.68
     s
    0.67
    nya
    0.62
     a
    0.60
    ]
    0.59
    ']
    0.58
     een
    0.58
    ]'
    0.57
     beträgt
    0.57
    $,
    0.57
    Activations Density 0.171%

    No Known Activations