© 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. 66920
    Prev
    Next
    INDEX
    Explanations

    Corporation Record Profile

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

    Daughter involved or Dental Health

    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
     ppl
    0.49
    ❽
    0.47
    ຈັດສົ່ງ
    0.46
    תר
    0.46
    \|=
    0.46
    𝟑
    0.46
     দৃঢ়
    0.46
     cuyos
    0.45
     отсут
    0.45
    ৮
    0.45
    POSITIVE LOGITS
     synt
    0.53
     यस
    0.51
    use
    0.50
    erian
    0.50
     biosynthetic
    0.49
     biosynthesis
    0.47
    ùng
    0.47
    <0x0D>
    0.46
    adex
    0.46
    ട്ടു
    0.44
    Activations Density 0.001%

    No Known Activations