© 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. 50368
    Prev
    Next
    INDEX
    Explanations

    Removing glue

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

    offers, instructions, safety

    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
     تیر
    0.53
     технологии
    0.52
    ἓ
    0.50
     በጥ
    0.50
     hùng
    0.49
     نیند
    0.49
     orientação
    0.48
     سک
    0.47
     جدید
    0.47
    rospection
    0.47
    POSITIVE LOGITS
    е
    0.48
    O
    0.45
    వే
    0.43
     de
    0.42
     sys
    0.42
    A
    0.42
    あえず
    0.41
    C
    0.41
    ƌ
    0.41
    ^{*
    0.40
    Activations Density 0.000%

    No Known Activations