© 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. 16047
    Prev
    Next
    INDEX
    Explanations

    Port Allegany, Pennsylvania

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

    areas: worth, piece, encoder, per, data

    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
     ન
    0.40
     Docsity
    0.40
     【
    0.39
    RxDocument
    0.39
    }}=-\
    0.38
    ।"
    0.38
    დესაც
    0.38
    ꒳
    0.38
     继续访问
    0.38
     ")
    0.38
    POSITIVE LOGITS
     ګرځ
    0.43
     características
    0.42
    urring
    0.42
    PROFILE
    0.42
     गहरे
    0.42
    creative
    0.41
    moniker
    0.41
     coração
    0.41
    arin
    0.41
     प्रेरणा
    0.40
    Activations Density 0.000%

    No Known Activations