© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10301
    Prev
    Next
    INDEX
    Explanations

    estimating amounts and qualities

    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
    endum
    0.99
    이
    0.89
    なかなか
    0.87
    library
    0.85
    aboration
    0.83
     للغاية
    0.81
     schließlich
    0.81
    ersk
    0.80
    UMENT
    0.79
     Przy
    0.79
    POSITIVE LOGITS
     shoving
    1.24
    ㄆ
    1.19
     modifiers
    1.18
     hola
    1.18
     Genres
    1.17
     impedances
    1.14
     Bhojpuri
    1.12
    UIActions
    1.12
     fontSize
    1.12
     ayarl
    1.12
    Activations Density 0.169%

    No Known Activations