© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 3106
    Prev
    Next
    INDEX
    Explanations

    python, import, code

    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
    ሀ
    0.48
     کیا
    0.47
    辔
    0.47
    ᑉ
    0.46
    なのです
    0.45
    ᱮ
    0.45
    Kia
    0.44
    Assumption
    0.44
    야
    0.44
    Cedar
    0.43
    POSITIVE LOGITS
    ht
    0.48
    os
    0.47
    ote
    0.44
     O
    0.43
    ror
    0.43
    oni
    0.42
    ored
    0.42
    ocl
    0.40
    oured
    0.40
     debuts
    0.40
    Activations Density 0.000%

    No Known Activations