© 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. 31-GEMMASCOPE-2-RES-262K
    7. 26815
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming terms

    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
    u
    0.52
    s
    0.50
    chand
    0.49
    dans
    0.48
    t
    0.46
    k
    0.45
    juan
    0.44
    dates
    0.44
    d
    0.44
    Maker
    0.43
    POSITIVE LOGITS
    ній
    0.47
    нца
    0.43
     cominc
    0.43
    носит
    0.42
    ޤ
    0.42
     แน
    0.41
    ೂರಿನ
    0.41
     permitirá
    0.40
    నుంది
    0.40
    랬
    0.40
    Activations Density 0.001%

    No Known Activations