© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3167
    Prev
    Next
    INDEX
    Explanations

    applying logic and knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    struck
    2.92
    ू
    2.82
     merupakan
    2.76
    ﺭ
    2.63
    bibfield
    2.59
    ल
    2.57
     bract
    2.55
    ከላከ
    2.48
    रा
    2.45
    сс
    2.45
    POSITIVE LOGITS
    isPlaying
    3.40
     dụng
    2.67
    EN
    2.54
    ﻢ
    2.49
     birlikte
    2.45
    yin
    2.42
    hashMap
    2.36
     mnie
    2.35
    程式
    2.34
    ણી
    2.31
    Activations Density 0.063%

    No Known Activations