© 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. 4196
    Prev
    Next
    INDEX
    Explanations

    That's it!

    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
    ج
    1.60
    ،
    1.46
    c
    1.33
     року
    1.31
     snapper
    1.19
    )})$
    1.18
    ，
    1.18
     однако
    1.16
     profundizar
    1.16
    ี
    1.16
    POSITIVE LOGITS
    م
    1.77
    К
    1.72
    ný
    1.51
    da
    1.49
    illing
    1.48
    мум
    1.48
    goers
    1.48
    de
    1.48
    dn
    1.45
    nous
    1.45
    Activations Density 0.029%

    No Known Activations