© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8900
    Prev
    Next
    INDEX
    Explanations

    boolean return values and 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_31_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
     награ
    0.46
    nętr
    0.46
     начну
    0.45
    ATHER
    0.45
    最好的
    0.45
    aña
    0.44
    𒌅
    0.43
    鉆
    0.43
     отец
    0.43
    pOt
    0.43
    POSITIVE LOGITS
     boolean
    1.13
     bool
    1.11
     Boolean
    1.11
    bool
    1.03
     false
    0.99
    boolean
    0.97
     Bool
    0.93
     False
    0.92
    Boolean
    0.92
     whether
    0.84
    Activations Density 0.250%

    No Known Activations