© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143308
    Prev
    Next
    INDEX
    Explanations

    verbs followed by 'to' or 'a'

    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
     seguramente
    0.48
     tropos
    0.46
     medición
    0.44
    ાઇન
    0.44
     fruto
    0.43
    ﻨ
    0.43
     reven
    0.43
     campione
    0.43
     (\$
    0.43
     automático
    0.43
    POSITIVE LOGITS
     ছ
    0.45
     For
    0.44
     sinks
    0.41
    For
    0.41
    anska
    0.40
     иска
    0.39
    孩
    0.39
    忔
    0.39
     লাগবে
    0.38
    ri
    0.38
    Activations Density 0.006%

    No Known Activations