© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 7909
    Prev
    Next
    INDEX
    Explanations

    lists, 't' or '4'list items containing numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    𝐀
    0.50
    ASS
    0.46
     Licence
    0.44
     slot
    0.43
     सपने
    0.43
     County
    0.42
    esley
    0.42
    😴
    0.42
    .
    0.42
    資訊
    0.41
    POSITIVE LOGITS
    ци
    0.49
    сед
    0.49
    </b>
    0.47
    со
    0.47
    bender
    0.44
    𝚣
    0.44
    倜
    0.43
    blocked
    0.43
     culturales
    0.43
    なが
    0.42
    Activations Density 0.000%

    No Known Activations