© 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. 12-GEMMASCOPE-2-RES-262K
    7. 44933
    Prev
    Next
    INDEX
    Explanations

    requests that can be answered or acted upon

    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
     poter
    1.58
    স
    1.40
    ਿ
    1.40
    です
    1.38
    ع
    1.38
    㐌
    1.38
    がい
    1.36
     thisobject
    1.34
    夂
    1.32
    ван
    1.31
    POSITIVE LOGITS
    Ch
    1.24
    Attention
    1.21
    MT
    1.20
    ),
    1.08
    Engine
    1.08
    >
    1.08
    Busy
    1.07
    PR
    1.06
    ेशन
    1.05
    eeper
    1.05
    Activations Density 0.013%

    No Known Activations