© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9403
    Prev
    Next
    INDEX
    Explanations

    Nelson and associated entities

    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
    isotropic
    3.28
    cations
    2.80
    ে
    2.63
    ح
    2.56
     convinced
    2.47
    cation
    2.46
    shader
    2.44
    메이션
    2.42
     unquestionably
    2.41
    े
    2.36
    POSITIVE LOGITS
    й
    2.91
    h
    2.80
    v
    2.15
    ка
    2.14
     همچ
    2.10
     सटे
    2.09
     уж
    2.05
    ovo
    2.03
     మంది
    1.97
     रोक
    1.96
    Activations Density 0.001%

    No Known Activations