© 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. 76770
    Prev
    Next
    INDEX
    Explanations

    listing contents

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

    including elements

    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
    le
    0.50
    es
    0.46
    ૨
    0.43
    ange
    0.42
    eers
    0.41
    ent
    0.41
    r
    0.41
    ੨
    0.40
    DIY
    0.39
    d
    0.39
    POSITIVE LOGITS
    INCLUDING
    0.52
     včetně
    0.50
     holotype
    0.47
     کرمان
    0.47
     金属
    0.46
     KMnO
    0.46
     omitting
    0.45
     including
    0.45
     roof
    0.45
     Including
    0.45
    Activations Density 0.001%

    No Known Activations