© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11081
    Prev
    Next
    INDEX
    Explanations

    basics and fundamentals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    מ
    2.39
    ק
    1.82
    ق
    1.81
    stuffs
    1.78
    र
    1.77
    го
    1.71
    ה
    1.70
    ﻘ
    1.70
    а
    1.68
    h
    1.65
    POSITIVE LOGITS
    lerine
    1.71
    metic
    1.60
    iciary
    1.55
    racht
    1.55
    ierra
    1.52
     basics
    1.50
    iality
    1.48
    lerini
    1.47
    ේෂ
    1.47
    ྥ
    1.45
    Activations Density 0.012%

    No Known Activations