© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35400
    Prev
    Next
    INDEX
    Explanations

    forbidden nature, place, love, fruit

    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
    ک
    1.65
    ನ್ನು
    1.64
    ка
    1.61
    ு
    1.54
    od
    1.49
    ми
    1.48
    ocomplete
    1.45
    ol
    1.43
     aren
    1.40
    iq
    1.40
    POSITIVE LOGITS
     poter
    1.98
    퐫
    1.86
    𝑨
    1.86
    锢
    1.85
    ');
    1.77
    핞
    1.77
    𝘴
    1.73
    𝘞
    1.73
    𝑫
    1.73
    }}$$
    1.71
    Activations Density 0.011%

    No Known Activations