© 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. 10808
    Prev
    Next
    INDEX
    Explanations

    user prompts

    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
    efined
    2.29
    ीय
    1.94
     unison
    1.94
    ഘ
    1.93
     MBS
    1.91
    hale
    1.87
    }^*
    1.85
    }=\
    1.79
    "}}>
    1.72
    Micro
    1.71
    POSITIVE LOGITS
     altro
    1.77
    ণ
    1.70
    вання
    1.67
    ๒
    1.66
    ité
    1.62
     reputations
    1.57
     subtiliter
    1.56
     linge
    1.54
     reprodu
    1.53
    nader
    1.53
    Activations Density 0.000%

    No Known Activations