© 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. 203252
    Prev
    Next
    INDEX
    Explanations

    celebrations, events, holidays, visits

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

    explaining concepts and lists

    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
    Enum
    0.50
     swamp
    0.48
     Object
    0.47
     identity
    0.45
     Else
    0.44
     Swamp
    0.43
     Identity
    0.43
    d
    0.42
    Identity
    0.41
     warp
    0.41
    POSITIVE LOGITS
    点の
    0.59
     দ্বিতীয়
    0.53
     اجمعين
    0.52
     दुसरे
    0.52
     அறிந்த
    0.52
     отмети
    0.51
     μία
    0.51
     nascita
    0.51
    并未
    0.50
     සිට
    0.50
    Activations Density 0.000%

    No Known Activations