© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28799
    Prev
    Next
    INDEX
    Explanations

    habitual or continuous actions

    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
    لاست
    0.43
    ড
    0.43
     använda
    0.41
    حن
    0.41
     evaluations
    0.40
     Linen
    0.40
    km
    0.40
     যাইতে
    0.40
     км
    0.39
     kroner
    0.39
    POSITIVE LOGITS
     کہ
    0.58
     cuya
    0.51
     ਮ
    0.49
     परन्तु
    0.49
     polizia
    0.49
     cuja
    0.48
     ambao
    0.47
     ਜੋ
    0.47
     ਸੁ
    0.46
    ッ
    0.46
    Activations Density 0.003%

    No Known Activations