© 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. 17568
    Prev
    Next
    INDEX
    Explanations

    manifesto, incendiary weapons

    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
    et
    1.08
    ale
    0.84
    ah
    0.84
    t
    0.82
     can
    0.81
    ala
    0.78
    p
    0.77
    ong
    0.75
    ali
    0.75
    pJ
    0.74
    POSITIVE LOGITS
    К
    0.65
    FROM
    0.65
    შე
    0.64
    他和
    0.63
    ですが
    0.63
    Avec
    0.61
    يا
    0.60
     과정
    0.59
    நீங்கள்
    0.59
    Ста
    0.58
    Activations Density 0.001%

    No Known Activations