© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8515
    Prev
    Next
    INDEX
    Explanations

    episode, town, today, tower

    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
     عمومی
    1.22
    Borderless
    1.14
    LAND
    1.14
    Attachment
    1.13
    CUT
    1.12
     Wider
    1.12
    ']->
    1.11
     Thorough
    1.11
    TouchableOpacity
    1.10
    ことがある
    1.09
    POSITIVE LOGITS
     lask
    1.32
    ো
    1.30
    ungkap
    1.29
     zlo
    1.28
     серед
    1.27
    adece
    1.27
     pericolo
    1.26
     darkness
    1.26
     parois
    1.25
     phận
    1.24
    Activations Density 0.000%

    No Known Activations