© 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. 138634
    Prev
    Next
    INDEX
    Explanations

    If, assume, openings, number format

    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
    s
    0.58
    K
    0.51
    most
    0.50
    农
    0.50
    rip
    0.48
    W
    0.47
    需要
    0.47
    Pet
    0.46
    r
    0.46
    less
    0.46
    POSITIVE LOGITS
    য়াত
    0.53
     دعوت
    0.48
     symbolizes
    0.47
     የተለያዩ
    0.46
     celebrates
    0.46
     veröffentlicht
    0.45
     Eintritt
    0.45
     বিশ্লেষণের
    0.44
     skiers
    0.44
     これは
    0.43
    Activations Density 0.002%

    No Known Activations