© 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. 21714
    Prev
    Next
    INDEX
    Explanations

    "the" followed by quotes or parentheses

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

    definitions in quotes or parentheses

    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
     குறிப்பிடத்தக்க
    0.49
    শির
    0.48
    caches
    0.46
    ಝ
    0.45
    aria
    0.43
     பெரும்பாலும்
    0.42
     Praia
    0.41
    থি
    0.41
    ś
    0.41
    obtenir
    0.40
    POSITIVE LOGITS
     severally
    0.51
    OV
    0.45
     enactment
    0.44
     член
    0.42
    EDY
    0.42
    ｢
    0.41
    ‘‘
    0.41
    ОВА
    0.41
     dilemmas
    0.41
    @"
    0.40
    Activations Density 0.008%

    No Known Activations