© 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. 3099
    Prev
    Next
    INDEX
    Explanations

    names of software or concepts

    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
    _
    0.98
    _.
    0.76
    ().
    0.74
    }.")
    0.71
    "/>.
    0.71
    もしくは
    0.70
    __.
    0.67
     mystery
    0.67
    ________________
    0.67
    __
    0.65
    POSITIVE LOGITS
     también
    1.66
     также
    1.65
     also
    1.62
     embodies
    1.60
     також
    1.52
     também
    1.51
     cũng
    1.51
     גם
    1.47
     exemplifies
    1.44
     همچنین
    1.43
    Activations Density 0.608%

    No Known Activations