Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 11964
    Prev
    Next
    INDEX
    Explanations

    enumerated items followed by parenthesis

    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_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
    От
    0.50
    あくまで
    0.45
    rakech
    0.43
     Nuremberg
    0.43
    antara
    0.42
     மறந்து
    0.42
    ל
    0.41
     Goodyear
    0.41
    ulho
    0.41
    от
    0.40
    POSITIVE LOGITS
     만
    0.46
     prolongation
    0.46
    )\
    0.45
     imposition
    0.45
     proposing
    0.44
     في
    0.43
     لأ
    0.43
    ूस
    0.42
     plans
    0.41
     nous
    0.41
    Activations Density 0.056%

    No Known Activations