© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11192
    Prev
    Next
    INDEX
    Explanations

    multiple digit sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     lại
    0.40
     ج
    0.38
     nuevamente
    0.38
    द्व
    0.36
     bij
    0.35
     ජ
    0.35
     gaf
    0.34
     снова
    0.34
     युग
    0.34
     га
    0.34
    POSITIVE LOGITS
    হ্যালো
    0.35
    paginate
    0.33
     //=>
    0.32
    they
    0.32
    𝒜
    0.32
    प्ताहिक
    0.30
    mol
    0.30
    particularly
    0.30
    ponente
    0.30
    awati
    0.30
    Activations Density 0.208%

    No Known Activations