© 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. 33069
    Prev
    Next
    INDEX
    Explanations

    locations or descriptions of places

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

    breakdown of what

    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
     действи
    0.49
     λ
    0.46
     실
    0.46
     정부
    0.45
     А
    0.45
     Lambda
    0.44
     нова
    0.44
     tę
    0.43
     lambda
    0.43
     член
    0.43
    POSITIVE LOGITS
    చె
    0.49
    ସ
    0.49
     atteindre
    0.48
    amingo
    0.47
    خ
    0.47
     nummer
    0.46
    धाम
    0.46
     upholstered
    0.46
    بلو
    0.46
    マト
    0.46
    Activations Density 0.000%

    No Known Activations