© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2374
    Prev
    Next
    INDEX
    Explanations

    insert into sorted array

    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_40_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
     शिक्षण
    0.44
     ocular
    0.40
     snakes
    0.39
     그렇게
    0.38
    citations
    0.38
     trich
    0.37
    Citation
    0.37
    窅
    0.37
     spectrometers
    0.37
     barrels
    0.36
    POSITIVE LOGITS
     ежеднев
    0.40
    мый
    0.38
    =(
    0.37
     penj
    0.37
    ní
    0.37
     uzak
    0.37
    ㄵ
    0.37
     большим
    0.36
    tható
    0.36
    +(
    0.36
    Activations Density 0.001%

    No Known Activations