© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3497
    Prev
    Next
    INDEX
    Explanations

    words ending in -able, -ive, -age, -ess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     because
    0.82
     ponieważ
    0.78
     mesmerizing
    0.71
     क्योंकि
    0.71
     menjelaskan
    0.71
     tarafından
    0.71
     वैसे
    0.69
    ↵↵
    0.68
     Although
    0.66
     karena
    0.66
    POSITIVE LOGITS
    ifiable
    0.90
    ukebox
    0.87
    ignement
    0.86
    ccess
    0.86
    agées
    0.85
    zzles
    0.85
    geries
    0.84
    giveness
    0.84
    rifuge
    0.84
    agerie
    0.83
    Activations Density 0.300%

    No Known Activations