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. 7309
    Prev
    Next
    INDEX
    Explanations

    walks into a/an

    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
    ന്ന
    1.17
    britannien
    1.13
    $-
    1.10
    res
    1.06
     mist
    1.06
    ੍ਹ
    1.05
    декс
    1.04
     href
    1.03
    era
    1.02
    ere
    0.99
    POSITIVE LOGITS
     Tatha
    1.48
    TextBox
    1.45
    pots
    1.45
     ㅅ
    1.43
     endeavours
    1.42
    Understand
    1.42
    ➠
    1.40
    anjay
    1.40
     dissati
    1.38
    Artists
    1.36
    Activations Density 0.000%

    No Known Activations