© 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. 8503
    Prev
    Next
    INDEX
    Explanations

    no access to tools or real-time information

    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
     sprayed
    0.49
     glob
    0.48
     evasion
    0.47
    یات
    0.47
    TextureAsset
    0.46
     invaded
    0.45
    =’
    0.45
     sentences
    0.44
     мая
    0.44
     negation
    0.44
    POSITIVE LOGITS
    ن
    0.50
     Samir
    0.48
    ل
    0.46
    Machine
    0.46
    ie
    0.45
    k
    0.44
     Fields
    0.44
    Method
    0.44
    Dream
    0.43
    SER
    0.43
    Activations Density 0.002%

    No Known Activations