© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205183
    Prev
    Next
    INDEX
    Explanations

    nanny, healthy, fractal, languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     cm
    0.45
     rea
    0.44
     birinci
    0.44
    }};
    0.42
    вна
    0.41
     axi
    0.41
     avi
    0.41
     phi
    0.40
     biosynthesis
    0.40
     disponible
    0.40
    POSITIVE LOGITS
    usst
    0.51
    created
    0.48
    områ
    0.48
    minify
    0.47
    ziest
    0.46
    आख
    0.46
    സ
    0.46
    сіб
    0.44
    णियों
    0.44
    地点
    0.44
    Activations Density 0.006%

    No Known Activations