© 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-16K
    7. 8696
    Prev
    Next
    INDEX
    Explanations

    bit and related technical terms

    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_16k_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
     возможность
    0.46
    TWI
    0.44
     Harb
    0.43
    لین
    0.43
    फो
    0.43
    ✕
    0.43
    Парт
    0.42
     Bryson
    0.42
    Variant
    0.42
    ierst
    0.42
    POSITIVE LOGITS
     bit
    0.68
     Bit
    0.63
    bit
    0.59
    Bit
    0.57
     bits
    0.55
    位
    0.55
     位
    0.52
     BIT
    0.51
     bitten
    0.46
     lj
    0.46
    Activations Density 0.076%

    No Known Activations