© 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. 166259
    Prev
    Next
    INDEX
    Explanations

    frequently used, still living, favorite alternative

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

    what happens

    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
    メーター
    0.45
    e
    0.44
    érard
    0.43
    Orange
    0.42
    iak
    0.42
     महाराजा
    0.42
    Martha
    0.42
     रोचक
    0.41
    ólicas
    0.41
    Jet
    0.41
    POSITIVE LOGITS
    잤
    0.50
     gradi
    0.50
     perspect
    0.49
     डिफ
    0.49
     appunto
    0.49
     difesa
    0.47
     adimensional
    0.47
     condens
    0.47
     dimensionless
    0.46
     ete
    0.46
    Activations Density 0.001%

    No Known Activations