© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7163
    Prev
    Next
    INDEX
    Explanations

    proxy, wrapper, pointer

    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_12_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
    ل
    2.03
    와의
    1.66
     وهذه
    1.58
     enthalpy
    1.57
    ם
    1.55
     itin
    1.54
    на
    1.53
    ীয়
    1.53
     sozinho
    1.53
    ᅴ
    1.52
    POSITIVE LOGITS
    }))
    1.77
    }";
    1.63
    を果た
    1.63
    inen
    1.58
    ০
    1.55
    ată
    1.55
    }|$
    1.55
    ták
    1.55
    dır
    1.54
     ويكيپيديا
    1.54
    Activations Density 0.057%

    No Known Activations