© 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. 163611
    Prev
    Next
    INDEX
    Explanations

    following words or phrases

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

    understanding, better, concentration, durable, reliable

    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
    alb
    0.48
    bay
    0.46
    ੀ
    0.46
    subsection
    0.46
    лика
    0.45
     ساعت
    0.44
    Dol
    0.44
    ن
    0.44
    exploration
    0.44
    phine
    0.43
    POSITIVE LOGITS
     spust
    0.51
    鱷
    0.49
     ప్రకట
    0.48
    matics
    0.45
     görd
    0.44
     ಕಂಚ
    0.43
    szön
    0.43
     monotonic
    0.43
     iniciando
    0.42
     kapcs
    0.42
    Activations Density 0.000%

    No Known Activations