© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17406
    Prev
    Next
    INDEX
    Explanations

    believes or believ

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

    word endings like -vation, -ive, -ure, -ing

    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
     Vortex
    0.44
     Volunteers
    0.41
     Volcano
    0.40
     Verb
    0.39
     Volunte
    0.39
    祟
    0.38
     Volumen
    0.38
     Alej
    0.37
     Veronica
    0.37
     .\
    0.37
    POSITIVE LOGITS
    ve
    1.71
    va
    1.56
    vi
    1.55
    vem
    1.54
    v
    1.52
    ves
    1.52
    вом
    1.51
    ве
    1.41
    vus
    1.41
    vo
    1.40
    Activations Density 0.163%

    No Known Activations