© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 6973
    Prev
    Next
    INDEX
    Explanations

    pivot selection

    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_24_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
    เพราะ
    0.51
     كما
    0.50
     लेकिन
    0.49
    隈
    0.48
     Maduro
    0.47
    !।
    0.46
     but
    0.46
     मगर
    0.46
     veremos
    0.46
    (!
    0.44
    POSITIVE LOGITS
     is
    0.55
     является
    0.55
     används
    0.55
     egensk
    0.53
     参数
    0.52
     corresponds
    0.52
     adjusts
    0.52
    ʼ
    0.51
     необхідно
    0.50
     denotes
    0.50
    Activations Density 0.008%

    No Known Activations