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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5602
    Prev
    Next
    INDEX
    Explanations

    words and phrases about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    .
    0.44
    ()
    0.43
     is
    0.41
    ]
    0.40
    ;
    0.40
    er
    0.40
    ?
    0.40
    ".
    0.38
     는
    0.38
    o
    0.38
    POSITIVE LOGITS
     sorts
    0.43
     süreç
    0.42
     personnes
    0.42
     durations
    0.41
    其實
    0.41
     potensi
    0.40
     nahezu
    0.40
     sensibles
    0.40
    relatively
    0.40
     provenant
    0.39
    Activations Density 0.045%

    No Known Activations