© 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. 441
    Prev
    Next
    INDEX
    Explanations

    praised for

    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
    skirts
    2.22
     instalments
    2.13
    是个
    2.12
    ストラ
    2.11
    сро
    2.10
    hoea
    2.05
    tener
    2.05
    ថ
    2.05
    タック
    2.03
    مند
    2.03
    POSITIVE LOGITS
    7
    2.04
    8
    1.86
    amen
    1.72
     singular
    1.71
    ancha
    1.70
    á
    1.68
     finite
    1.62
    enen
    1.61
     ambient
    1.61
    6
    1.59
    Activations Density 0.036%

    No Known Activations