© 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. 11079
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    ées
    1.02
     edifice
    0.97
    🈷
    0.97
    ­
    0.95
     entrée
    0.95
     organizes
    0.95
    🛂
    0.95
    🈚
    0.91
    èques
    0.90
    ée
    0.89
    POSITIVE LOGITS
    0
    1.02
    2
    1.00
    4
    0.98
     rekao
    0.97
    5
    0.94
    3
    0.88
    7
    0.88
    𝙙
    0.87
    ので
    0.87
    1
    0.87
    Activations Density 0.293%

    No Known Activations