© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3115
    Prev
    Next
    INDEX
    Explanations

    code, math, or latex

    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_29_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
    سته
    0.65
    并在
    0.59
    ำ
    0.59
     institu
    0.58
    Length
    0.57
    一般
    0.57
    ത്തില
    0.54
     जोड
    0.54
    fabrik
    0.53
     generally
    0.53
    POSITIVE LOGITS
    textbackslash
    0.88
    $-$,
    0.86
    |_{\
    0.85
    }]$,
    0.85
    |^{\
    0.84
    皞
    0.83
    operatorname
    0.82
    prime
    0.82
    |_{
    0.82
    ]$-
    0.81
    Activations Density 0.131%

    No Known Activations