© 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. 224450
    Prev
    Next
    INDEX
    Explanations

    adjusted for inequalities

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

    quality, Horizon, few hours, friendly, build, Vogel, found

    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
     Angus
    0.55
     пас
    0.47
     पार
    0.46
     ठर
    0.45
     קי
    0.44
     จง
    0.44
     ผ
    0.43
     ଆ
    0.43
     augmenting
    0.42
     appending
    0.42
    POSITIVE LOGITS
    、
    0.61
    тельного
    0.49
    тельной
    0.47
    俅
    0.47
    тивной
    0.45
    ющего
    0.45
    વવા
    0.45
    millimeters
    0.44
    options
    0.43
    OWN
    0.43
    Activations Density 0.001%

    No Known Activations