© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6430
    Prev
    Next
    INDEX
    Explanations

    forms words ending in -ic, -ics, -ical

    np_acts-logits-general · gemini-2.5-flash-lite

    words ending in ic or ics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    퓸
    0.41
    ataire
    0.41
    ştur
    0.39
    atori
    0.38
    adoria
    0.38
    voren
    0.37
     निर्देशा
    0.37
    朤
    0.36
    şa
    0.36
     Fourteenth
    0.36
    POSITIVE LOGITS
    ics
    2.59
    ic
    2.55
    ically
    2.41
    ick
    2.20
    IC
    2.19
    ICS
    2.13
    ical
    2.06
    ICs
    2.06
    ica
    1.98
    یک
    1.95
    Activations Density 0.162%

    No Known Activations