© 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. 111195
    Prev
    Next
    INDEX
    Explanations

    code execution, multilingual content

    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
    ostr
    0.41
     revise
    0.40
    Max
    0.38
    <h3>
    0.37
    max
    0.37
    STRUCTION
    0.36
    やはり
    0.35
    multi
    0.34
    atoi
    0.34
     गठबंधन
    0.34
    POSITIVE LOGITS
    甬
    0.42
     Elektrokh
    0.41
     отмети
    0.39
     κοινων
    0.38
     mata
    0.38
     노트
    0.38
     NHE
    0.38
     Pé
    0.38
     éxitos
    0.37
    rdquo
    0.37
    Activations Density 0.000%

    No Known Activations