© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2198
    Prev
    Next
    INDEX
    Explanations

    of or to followed by common words

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

    following articles

    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
     começou
    0.31
    ৌম
    0.31
    絴
    0.31
    中所
    0.31
    ﻭ
    0.30
    の高
    0.30
    quando
    0.30
    வின்
    0.30
    وقال
    0.30
    வும்
    0.30
    POSITIVE LOGITS
    ...
    0.39
     others
    0.38
    ...”
    0.36
     ’
    0.35
     konuda
    0.33
     publicized
    0.32
     his
    0.32
    ften
    0.32
     heck
    0.32
    …
    0.32
    Activations Density 0.504%

    No Known Activations