© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2705
    Prev
    Next
    INDEX
    Explanations

    sharp edges, corners, and points

    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
    ্লাহ
    1.80
    liness
    1.73
    rabbitmq
    1.59
    ক
    1.57
     Infatti
    1.56
    יות
    1.55
    𝙠
    1.55
    郸
    1.52
    客様
    1.50
    的情況
    1.49
    POSITIVE LOGITS
    SOR
    1.57
    ast
    1.55
    خ
    1.52
    ES
    1.48
    STRONG
    1.41
    ED
    1.40
    你
    1.38
    на
    1.38
    el
    1.35
    도
    1.32
    Activations Density 0.005%

    No Known Activations