© 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. 16-GEMMASCOPE-2-RES-262K
    4. 110016
    Prev
    Next
    INDEX
    Explanations

    Miles Morales, network addresses, Pride Lands

    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_16_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
    c
    0.86
    m
    0.65
    t
    0.61
    cD
    0.60
     출시
    0.59
     Indicates
    0.58
    b
    0.57
    𝗰
    0.57
    cG
    0.56
    ade
    0.55
    POSITIVE LOGITS
     hateful
    0.61
     hate
    0.56
    थि
    0.52
     paranoid
    0.52
     diaspora
    0.51
     hairs
    0.50
     heinous
    0.49
     unbreakable
    0.49
     prejudice
    0.48
    АТО
    0.48
    Activations Density 0.000%

    No Known Activations