© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2462
    Prev
    Next
    INDEX
    Explanations

    common phrases and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     방법에
    1.87
     เวอร์ชั่น
    1.81
    タック
    1.80
     방법을
    1.77
     Older
    1.73
    맬
    1.72
    捱
    1.72
    𝒓
    1.71
    トリック
    1.71
     어린
    1.71
    POSITIVE LOGITS
    7
    2.08
    4
    2.00
    8
    2.00
    6
    1.98
    3
    1.82
    5
    1.72
    9
    1.64
    eight
    1.53
    seven
    1.40
    2
    1.39
    Activations Density 0.165%

    No Known Activations