© 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. 128785
    Prev
    Next
    INDEX
    Explanations

    technical level explanations

    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
    applied
    0.50
    called
    0.49
    usually
    0.46
    typically
    0.46
    f
    0.46
    subcategory
    0.45
    related
    0.44
    culture
    0.44
    supplied
    0.44
    ísticos
    0.44
    POSITIVE LOGITS
    蜞
    0.48
     স্বীকৃতি
    0.45
     اگر
    0.44
    際には
    0.44
    ؑ
    0.44
     *@
    0.44
     灬
    0.42
     фізи
    0.42
     szükséges
    0.42
    iai
    0.42
    Activations Density 0.004%

    No Known Activations