© 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. 17-GEMMASCOPE-2-RES-16K
    7. 16096
    Prev
    Next
    INDEX
    Explanations

    ScrollView components and code blocks

    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_17_width_16k_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
    ริม
    0.87
     angesch
    0.85
    ༌
    0.84
    halb
    0.84
    ශ්
    0.83
    윽
    0.83
    जनक
    0.83
    ો
    0.82
     vyh
    0.80
    <%=
    0.78
    POSITIVE LOGITS
     деше
    0.98
    ರ್ಚ
    0.95
    .".,
    0.94
    ন্থ
    0.91
     fürs
    0.89
     следующее
    0.88
     turbines
    0.87
     inny
    0.85
     cockpit
    0.85
     aterriz
    0.85
    Activations Density 0.000%

    No Known Activations