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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53047
    Prev
    Next
    INDEX
    Explanations

    follow the order of operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    zett
    0.63
    andr
    0.62
    print
    0.58
     Haley
    0.57
     Zeits
    0.57
     fair
    0.57
     Geißler
    0.56
     콘
    0.56
     grain
    0.56
     ٹ
    0.55
    POSITIVE LOGITS
    Fixed
    0.69
     জর্জ
    0.66
     Fixed
    0.63
    Fix
    0.63
    सिर
    0.62
     Hate
    0.61
    र्भ
    0.61
     వ్యవస్థ
    0.60
    cry
    0.60
     ({\
    0.60
    Activations Density 0.003%

    No Known Activations