© 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. 8878
    Prev
    Next
    INDEX
    Explanations

    don't, doesn't

    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
    \">
    0.65
    tau
    0.61
    +:
    0.60
    age
    0.59
    ្នែក
    0.59
    ination
    0.58
    ]}{\
    0.58
    $",
    0.57
     miljoen
    0.57
    ﻘ
    0.57
    POSITIVE LOGITS
     Equally
    0.57
    ियल
    0.57
    ı
    0.57
    們
    0.57
     equally
    0.56
     belanja
    0.56
    ン
    0.56
    没有人
    0.55
    जैसा
    0.55
     ພວກເຮົາ
    0.55
    Activations Density 0.020%

    No Known Activations