© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 19770
    Prev
    Next
    INDEX
    Explanations

    deep, depth, deeper, deepest

    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_53_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
    ഗണ
    0.38
    ട്ട്
    0.36
    انیہ
    0.36
    クトル
    0.33
    犃
    0.33
    aniye
    0.32
    प्ताहिक
    0.32
    тын
    0.31
    聒
    0.31
    mbito
    0.31
    POSITIVE LOGITS
     deep
    4.56
     Deep
    4.25
    deep
    4.25
    Deep
    4.25
    深
    4.19
     깊
    4.06
     глубо
    3.92
    深度
    3.84
     deeper
    3.72
     deepest
    3.59
    Activations Density 0.285%

    No Known Activations