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. 7245
    Prev
    Next
    INDEX
    Explanations

    web and its applications

    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
     UAS
    2.79
    വ
    2.74
    a
    2.73
    েম
    2.60
     FFT
    2.58
    ാപ
    2.50
    leistung
    2.50
     млад
    2.45
    брь
    2.42
     trasero
    2.38
    POSITIVE LOGITS
    nesday
    3.13
     surpassing
    2.70
    isode
    2.69
    툰
    2.60
    ไซต์
    2.58
     contradicting
    2.56
    ಕರ್
    2.53
     liked
    2.52
    ских
    2.52
    reathe
    2.50
    Activations Density 0.082%

    No Known Activations