© 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. 92753
    Prev
    Next
    INDEX
    Explanations

    often followed by verbs/prepositions

    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
    мага
    0.46
     Deficiency
    0.46
     केंद्र
    0.45
    饬
    0.44
    %
    0.44
     personalizada
    0.43
    icient
    0.43
    ам
    0.42
    ustes
    0.42
    setting
    0.42
    POSITIVE LOGITS
    ለያዩ
    0.40
     animale
    0.39
     addirittura
    0.38
     sessionId
    0.37
     aprire
    0.37
     breeding
    0.36
    一只
    0.36
    カナ
    0.36
     therapy
    0.36
    莉
    0.36
    Activations Density 0.004%

    No Known Activations