© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 293
    Prev
    Next
    INDEX
    Explanations

    offensive play search though few days

    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
     rém
    2.40
    ungannya
    2.36
    сро
    2.28
    astic
    2.28
     both
    2.25
    様子
    2.23
    ﹗
    2.20
     (’
    2.17
    蜊
    2.14
    кает
    2.13
    POSITIVE LOGITS
    7
    4.33
    0
    4.15
    8
    4.13
    4
    4.12
    6
    4.05
    5
    4.00
    9
    3.74
    3
    3.62
    nd
    3.55
    º
    3.09
    Activations Density 0.366%

    No Known Activations