© 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. 5643
    Prev
    Next
    INDEX
    Explanations

    unique proper nouns

    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
    asmuch
    0.36
    Non
    0.35
    VL
    0.33
    fold
    0.33
    tenths
    0.32
    ంబేద్కర్
    0.31
    𒋀
    0.31
    volent
    0.31
    АН
    0.31
    AKES
    0.31
    POSITIVE LOGITS
     Każ
    0.35
     adlı
    0.32
     Министерства
    0.32
     dhe
    0.31
    ا
    0.31
     Horticulture
    0.31
     airfield
    0.30
    烫
    0.30
    કર
    0.30
    સ
    0.30
    Activations Density 0.008%

    No Known Activations