© 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. 28151
    Prev
    Next
    INDEX
    Explanations

    survival reproduction

    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
     phosphory
    0.50
    ΕΙ
    0.48
     cytotoxicity
    0.47
    ちなみに
    0.46
     fixa
    0.46
     unsecured
    0.45
     hyperglycemia
    0.45
    𐰣
    0.45
     neoplas
    0.45
     inactivation
    0.45
    POSITIVE LOGITS
    ahs
    0.45
    wed
    0.43
    ractive
    0.43
    jar
    0.42
    wie
    0.42
    slack
    0.42
     Sahib
    0.42
     Hispanic
    0.42
    matic
    0.41
     Latino
    0.41
    Activations Density 0.004%

    No Known Activations