© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2536
    Prev
    Next
    INDEX
    Explanations

    converting text or images

    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_22_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
    ige
    0.52
    an
    0.52
    r
    0.50
    u
    0.47
    k
    0.46
    h
    0.45
    z
    0.44
    am
    0.44
    ch
    0.43
    is
    0.43
    POSITIVE LOGITS
     Verifica
    0.49
    받
    0.47
     PropTypes
    0.47
     Verificar
    0.45
     waterfowl
    0.45
    larınız
    0.44
     BFF
    0.44
     phishing
    0.43
     corollary
    0.43
     받
    0.42
    Activations Density 0.000%

    No Known Activations