© 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. 100929
    Prev
    Next
    INDEX
    Explanations

    followed by specific words

    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
    薫
    0.47
    載
    0.46
    лан
    0.45
     komfort
    0.44
     anticipate
    0.43
    مله
    0.43
    Ту
    0.43
     आत्मनिर्भर
    0.43
    荷重
    0.43
    વતી
    0.42
    POSITIVE LOGITS
    elen
    0.42
     Malayalam
    0.40
    tia
    0.40
    cB
    0.40
     pomocí
    0.40
    睑
    0.40
    ntz
    0.39
    isatie
    0.39
     Wochschr
    0.39
     স্প
    0.38
    Activations Density 0.005%

    No Known Activations