© 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-262K
    7. 11356
    Prev
    Next
    INDEX
    Explanations

    raise ValueError, starts with

    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_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
     spectrometers
    1.32
    it
    1.30
    蒡
    1.23
     arbitrage
    1.21
    carbonyl
    1.20
    ти
    1.18
    িণী
    1.18
    permutation
    1.18
    та
    1.17
    тар
    1.14
    POSITIVE LOGITS
    )]),
    1.18
     pomen
    1.14
    ipio
    1.12
     principais
    1.12
     Furthermore
    1.10
    して
    1.09
     Moreover
    1.09
    嫖
    1.08
    yzed
    1.08
     ベージュ
    1.07
    Activations Density 0.000%

    No Known Activations