© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1363
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    Aim
    0.59
     müm
    0.57
    </tr>
    0.56
     glory
    0.55
    を目指
    0.55
     metaphysical
    0.55
     Aim
    0.55
     conject
    0.54
    摹
    0.54
     CrL
    0.54
    POSITIVE LOGITS
     recommend
    1.23
     recommending
    1.17
     RECOMMEND
    1.16
     recomend
    1.13
     recommand
    1.13
    Recommend
    1.13
     Recommend
    1.09
     recomand
    1.09
    recommend
    1.07
     recommends
    1.06
    Activations Density 0.212%

    No Known Activations