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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52388
    Prev
    Next
    INDEX
    Explanations

    semantic units after common sequence starters

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

    individuals involved

    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_262k_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
    Kep
    0.46
    OE
    0.46
    œ
    0.44
     Với
    0.44
    heres
    0.44
    Mapper
    0.43
    OP
    0.43
    心が
    0.42
     Jazeera
    0.41
    Whilst
    0.41
    POSITIVE LOGITS
    ப்பையும்
    0.57
    腖
    0.55
     publiés
    0.51
    㶪
    0.51
     downregulated
    0.49
    usst
    0.48
    醗
    0.48
    堭
    0.48
    orious
    0.47
     сезона
    0.46
    Activations Density 0.000%

    No Known Activations