© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    keywords + related concepts

    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
    。
    0.79
    \".
    0.68
    .\"
    0.63
    .
    0.62
    ।
    0.61
    }$.
    0.61
    ።
    0.61
    ”。
    0.59
    ().
    0.59
    ).
    0.57
    POSITIVE LOGITS
     is
    0.58
     είναι
    0.57
     isn
    0.54
     onus
    0.54
     could
    0.53
     thing
    0.53
     was
    0.51
     infringer
    0.51
     doesn
    0.51
    数は
    0.50
    Activations Density 0.011%

    No Known Activations