© 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. 165517
    Prev
    Next
    INDEX
    Explanations

    new form or component

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

    MsgBox contents

    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
    ുകെ
    0.51
    на
    0.47
    Ци
    0.45
    blurred
    0.44
    чув
    0.44
    atini
    0.43
    ⇩
    0.42
    học
    0.42
    ayit
    0.41
    хову
    0.40
    POSITIVE LOGITS
    '
    0.54
     folyt
    0.51
     viste
    0.49
     devam
    0.48
     fosse
    0.47
     demuestra
    0.44
     duas
    0.43
    之一
    0.43
     foli
    0.42
     continuar
    0.42
    Activations Density 0.000%

    No Known Activations