© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15929
    Prev
    Next
    INDEX
    Explanations

    text formatting characters

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

    But lacks or however

    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_31_width_16k_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
     periodical
    0.48
    誑
    0.46
     sprink
    0.45
     dole
    0.42
     repertoire
    0.42
    }$&$
    0.41
    碴
    0.41
     schm
    0.41
    大
    0.40
    AMERICAN
    0.40
    POSITIVE LOGITS
    ogenetic
    0.50
     Goni
    0.46
     FAU
    0.46
    ப்படாத
    0.45
     chaotic
    0.45
    avik
    0.45
    ie
    0.45
    ne
    0.45
     बहादुर
    0.45
     каким
    0.45
    Activations Density 0.003%

    No Known Activations