© 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. 50602
    Prev
    Next
    INDEX
    Explanations

    travel and costs

    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
    <unused79>
    0.49
     ഉയർന്ന
    0.49
     verschiedenen
    0.47
     Teile
    0.47
     eines
    0.47
     Nieder
    0.45
     verschied
    0.45
     Küchen
    0.45
     जिसने
    0.44
     bewusst
    0.44
    POSITIVE LOGITS
    ETHER
    0.51
    ENT
    0.45
     apesar
    0.45
    ưng
    0.44
     propietarios
    0.44
    。
    0.42
     AGAIN
    0.42
    dicke
    0.41
    тому
    0.41
    '
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.