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. 7284
    Prev
    Next
    INDEX
    Explanations

    collision detection

    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
     denn
    2.70
    ความ
    2.56
    ष्मान
    2.53
     inclination
    2.53
     uitle
    2.51
     aloud
    2.46
    <bos>
    2.45
    ेक्ट
    2.41
     том
    2.34
     coroner
    2.31
    POSITIVE LOGITS
    at
    3.40
    ना
    2.94
    на
    2.77
     liés
    2.73
     rejoint
    2.71
    𝜃
    2.68
    ف
    2.66
    kost
    2.63
     LHC
    2.61
    nutí
    2.54
    Activations Density 0.035%

    No Known Activations