© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    Spanish/Portuguese or other languages

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

    phonetic spellings and foreign words

    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
    ﻚ
    0.23
     apricot
    0.23
     vacations
    0.22
     wher
    0.22
     westerly
    0.21
     turntable
    0.21
     sweets
    0.21
     DMV
    0.21
     BNB
    0.21
    ᅭ
    0.21
    POSITIVE LOGITS
    ici
    0.20
    ru
    0.20
    ic
    0.20
    bin
    0.19
    un
    0.19
    la
    0.19
    oni
    0.18
    ramient
    0.18
    eni
    0.18
    ir
    0.18
    Activations Density 0.153%

    No Known Activations