© 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. 197489
    Prev
    Next
    INDEX
    Explanations

    it is to be appreciated that

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

    technical and financial terms

    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
    纍
    0.55
     rodziny
    0.51
     popol
    0.49
    羣
    0.48
     GoName
    0.47
     لق
    0.45
    菁
    0.45
    蒐
    0.44
    ACIÓN
    0.44
    璁
    0.44
    POSITIVE LOGITS
     commendable
    0.44
     insisted
    0.42
    branded
    0.42
    ruled
    0.42
     notably
    0.41
    owned
    0.41
     refused
    0.41
    anya
    0.41
    マガ
    0.40
     DA
    0.40
    Activations Density 0.000%

    No Known Activations