Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6850
    Prev
    Next
    INDEX
    Explanations

    non-English characters and symbols

    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
    outcome
    0.52
     dependen
    0.47
    桦
    0.46
     allons
    0.43
    dominant
    0.43
     Martina
    0.43
    aughton
    0.43
    turns
    0.43
    duty
    0.42
    propion
    0.42
    POSITIVE LOGITS
    的可
    0.48
     σε
    0.47
    瞩
    0.46
     μπορεί
    0.45
     পৃথক
    0.44
    rę
    0.44
    矚
    0.43
    ခြေ
    0.42
     γνω
    0.41
    🐱
    0.41
    Activations Density 0.000%

    No Known Activations