Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 965
    Prev
    Next
    INDEX
    Explanations

    explicit language or adult themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     速
    1.63
    jeli
    1.59
    сро
    1.57
     historians
    1.56
    [*][[
    1.55
     Quir
    1.49
     Zo
    1.49
    ................
    1.48
     schemes
    1.45
     期
    1.44
    POSITIVE LOGITS
    7
    3.21
    6
    3.13
    8
    3.09
    9
    2.81
    5
    2.74
    3
    2.70
    4
    2.68
    0
    2.34
    2
    2.06
    1
    1.97
    Activations Density 0.111%

    No Known Activations