© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 557
    Prev
    Next
    INDEX
    Explanations

    generate, be, on, so, need

    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
    getImageFolder
    0.87
    䤃
    0.81
    getRedTeam
    0.79
    ColorBit
    0.75
    ઐ
    0.74
    Ɵ
    0.74
    젹
    0.73
    ᖕ
    0.72
    㶪
    0.72
    䔧
    0.71
    POSITIVE LOGITS
     you
    1.16
    )
    1.05
    ),
    0.98
     they
    0.92
     but
    0.90
     will
    0.90
     it
    0.90
    ).
    0.88
     we
    0.86
     the
    0.85
    Activations Density 0.015%

    No Known Activations