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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8750
    Prev
    Next
    INDEX
    Explanations

    Objective-C initWithFrame, spectrophotometer

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific measurement or imaging terms related to spectrophotometry and device initialization.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    镦
    -3.89
    ؟
    -3.34
    饪
    -3.30
    涠
    -3.17
    ൎ
    -3.13
    踯
    -3.03
    geſ
    -2.97
    閦
    -2.95
    觧
    -2.92
    甞
    -2.91
    POSITIVE LOGITS
     The
    3.41
    ↵↵
    3.33
     —
    3.23
    ↵
    3.19
    t
    2.84
    *
    2.75
    '
    2.67
    "
    2.64
    ,"
    2.61
    ll
    2.59
    Activations Density 0.019%

    No Known Activations