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-65K
    4. 2516
    Prev
    Next
    INDEX
    Explanations

    std:: and Console

    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_65k_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
     کي
    0.54
    ")]
    0.52
    rop
    0.51
    kina
    0.50
    }")]
    0.50
     _|
    0.49
     {}".
    0.48
     Möbius
    0.48
    förm
    0.47
    כו
    0.47
    POSITIVE LOGITS
    ::
    0.70
    ത്തിലും
    0.57
    ·
    0.53
    த்திலும்
    0.50
    aksanakan
    0.49
    ]::
    0.49
    もお
    0.49
    にも
    0.48
    ങ്ങളിലും
    0.46
     নিষ্পত্তি
    0.46
    Activations Density 0.096%

    No Known Activations