© 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. 34928
    Prev
    Next
    INDEX
    Explanations

    hotel descriptions and conditions

    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
    ामुळे
    1.72
    THING
    1.65
    ians
    1.63
    s
    1.63
    aus
    1.52
    по
    1.50
    iest
    1.50
    ੀ
    1.47
    ের
    1.45
    sas
    1.40
    POSITIVE LOGITS
    ان
    2.16
    个
    1.61
    ৪
    1.49
    ー
    1.48
    на
    1.47
    сть
    1.40
     Edelstahl
    1.37
    cı
    1.36
    ۔
    1.36
    𝒄
    1.34
    Activations Density 0.001%

    No Known Activations