© 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. 5175
    Prev
    Next
    INDEX
    Explanations

    equation result

    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
    :
    0.57
     hereafter
    0.48
    ,
    0.47
    icht
    0.43
    ependent
    0.42
     issuing
    0.41
    ヱ
    0.41
     da
    0.41
     deut
    0.40
     Europ
    0.40
    POSITIVE LOGITS
     Also
    0.66
    Also
    0.66
     Like
    0.61
    Thanks
    0.58
    Like
    0.58
    Everyone
    0.58
    They
    0.57
    Well
    0.57
    You
    0.56
    That
    0.55
    Activations Density 0.006%

    No Known Activations