© 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. 16-GEMMASCOPE-2-RES-262K
    7. 142245
    Prev
    Next
    INDEX
    Explanations

    crisis, suicidal ideation, surface, spontaneous interaction, Hindi phrases, Spanish, timing

    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
    粕
    0.51
    គ្រឿង
    0.50
    essive
    0.50
    琙
    0.48
    otation
    0.47
    𝗍
    0.47
    魯
    0.46
    etem
    0.45
    崢
    0.45
    梩
    0.45
    POSITIVE LOGITS
     tapped
    0.45
     Tìm
    0.45
    "));
    0.45
     batted
    0.44
     revamped
    0.43
     ‎
    0.43
    われます
    0.43
     vuole
    0.42
     repaired
    0.42
     chromed
    0.42
    Activations Density 0.000%

    No Known Activations