© 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. 31-GEMMASCOPE-2-RES-262K
    7. 17783
    Prev
    Next
    INDEX
    Explanations

    based on

    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_31_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
     jod
    0.51
    ></
    0.47
     CPD
    0.46
     ni
    0.45
     MS
    0.44
     sliced
    0.44
     VIT
    0.44
    e
    0.44
    웃
    0.44
     unplanned
    0.43
    POSITIVE LOGITS
    піль
    0.49
     frá
    0.47
    dbContext
    0.46
     nécessité
    0.46
     বাহাদুর
    0.46
    ကြာ
    0.45
    ä
    0.45
    dlg
    0.44
    }):=\
    0.43
    ្នក
    0.43
    Activations Density 0.000%

    No Known Activations