© 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. 22630
    Prev
    Next
    INDEX
    Explanations

    likely conditional statements

    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
    Motor
    0.45
    㝌
    0.43
    ೬
    0.42
    RestController
    0.42
     zweite
    0.41
    Instance
    0.40
     لوگوں
    0.40
    Leggi
    0.40
    𒀀
    0.40
    SpringMVCProject
    0.40
    POSITIVE LOGITS
     potentially
    0.48
     likely
    0.48
     quirky
    0.47
     typically
    0.44
     including
    0.43
     perhaps
    0.41
     možda
    0.41
     conceivably
    0.40
     maybe
    0.40
     especially
    0.39
    Activations Density 0.016%

    No Known Activations