© 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. 261
    Prev
    Next
    INDEX
    Explanations

    control of

    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
    which
    0.25
     which
    0.24
     are
    0.22
    py
    0.21
     probablement
    0.21
    0.21
     I
    0.21
    v
    0.21
     =
    0.20
    tl
    0.20
    POSITIVE LOGITS
    ในการ
    0.33
     بشأن
    0.30
     při
    0.29
     terhadap
    0.28
    กับการ
    0.26
     về
    0.26
     với
    0.25
     تجاه
    0.25
     atuação
    0.25
     vào
    0.24
    Activations Density 7.062%

    No Known Activations