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. 9-GEMMASCOPE-2-RES-262K
    4. 7315
    Prev
    Next
    INDEX
    Explanations

    nationalities and groups of people

    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_9_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
    tained
    1.75
    ている
    1.72
    ten
    1.64
    able
    1.63
    tting
    1.63
    ся
    1.61
    tt
    1.59
    ো
    1.58
    erte
    1.55
    to
    1.55
    POSITIVE LOGITS
     positrons
    2.16
    犸
    2.11
    ons
    2.01
    htp
    1.99
    िंक
    1.98
    ometimes
    1.98
     estrogens
    1.97
    QUARE
    1.89
    ynthesis
    1.87
    ફેદ
    1.84
    Activations Density 0.086%

    No Known Activations