© 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. 100153
    Prev
    Next
    INDEX
    Explanations

    text format

    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
    ah
    0.46
     nouvel
    0.45
    ar
    0.44
    er
    0.43
    o
    0.43
    ਨ
    0.42
    ions
    0.42
     страница
    0.42
    vet
    0.41
    ell
    0.41
    POSITIVE LOGITS
     ఛ
    0.40
     ਨਾਲ
    0.39
     //</
    0.39
     نسبت
    0.39
    ंदन
    0.37
     चरम
    0.36
    кры
    0.36
     사람
    0.36
    charCode
    0.36
     만든
    0.36
    Activations Density 0.004%

    No Known Activations