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. 550
    Prev
    Next
    INDEX
    Explanations

    explanation:

    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
     marchés
    0.43
    ່ມ
    0.40
     variétés
    0.39
     rameaux
    0.39
     種
    0.38
     sucr
    0.38
     childnya
    0.38
     antennis
    0.37
     condiment
    0.37
    োগ্রাফ
    0.37
    POSITIVE LOGITS
    The
    0.56
    This
    0.55
    If
    0.50
    Each
    0.49
    It
    0.48
    While
    0.47
    Although
    0.47
    Only
    0.47
    //
    0.46
    Not
    0.44
    Activations Density 0.145%

    No Known Activations