© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154480
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers, skills, finance, business systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嬪
    0.46
    ড়া
    0.44
    thood
    0.42
    疗
    0.41
     throwable
    0.41
     rubbed
    0.40
    👧
    0.40
    ర్థి
    0.40
     வழங்க
    0.40
     moles
    0.40
    POSITIVE LOGITS
     훨
    0.52
     내용
    0.47
     gosto
    0.47
     กลุ่ม
    0.47
     espaço
    0.47
     геометри
    0.47
     EMU
    0.47
    সভাপতি
    0.46
     geometri
    0.46
    xton
    0.46
    Activations Density 0.000%

    No Known Activations