© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2189
    Prev
    Next
    INDEX
    Explanations

    numerical divisibility checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     شیخ
    0.41
    ๓
    0.40
     magar
    0.39
     magnetite
    0.38
     Prosecution
    0.38
     ૩
    0.38
    ³)
    0.38
    ISTRATION
    0.37
    <unused36>
    0.36
     ､
    0.36
    POSITIVE LOGITS
     |=
    0.37
     п
    0.35
    >>
    0.34
     Resources
    0.34
    BYTE
    0.34
    bytes
    0.34
     >>
    0.33
     ByteBuffer
    0.32
    béco
    0.32
     :=
    0.32
    Activations Density 0.005%

    No Known Activations