© 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. 9313
    Prev
    Next
    INDEX
    Explanations

    Linq; in C# code

    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
    ۥ
    1.90
    athermy
    1.87
    =>{
    1.78
    ்துறை
    1.76
    सिव
    1.71
    thousand
    1.70
    ColorEffects
    1.63
    monotonic
    1.60
    ponente
    1.58
     predis
    1.56
    POSITIVE LOGITS
    us
    2.34
    as
    2.19
    or
    2.10
    ell
    2.08
    𝓾
    2.05
    ig
    1.99
    in
    1.91
    ו
    1.89
    ing
    1.88
    ه
    1.87
    Activations Density 0.000%

    No Known Activations