© 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. 182737
    Prev
    Next
    INDEX
    Explanations

    transitional period

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

    explanation of concepts

    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
     কণ
    0.49
    <0x0D>
    0.43
    bés
    0.42
     فائلوں
    0.42
    грама
    0.41
    father
    0.41
    sourced
    0.41
    credits
    0.41
    cpf
    0.41
    ڑ
    0.41
    POSITIVE LOGITS
     방법을
    0.46
     excavations
    0.46
     மனு
    0.45
     previewBuilder
    0.45
     articulation
    0.45
     desarrollar
    0.44
     trasera
    0.44
     diseñar
    0.42
     управления
    0.42
     మాత్రం
    0.42
    Activations Density 0.000%

    No Known Activations