© 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. 227504
    Prev
    Next
    INDEX
    Explanations

    stunning ready, organic food, VPN client

    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
    ева
    0.47
     Facilit
    0.46
    ces
    0.46
     Sensory
    0.44
    会上
    0.44
    ورا
    0.43
    춘
    0.42
    哭
    0.41
    Spatial
    0.41
     Tiếp
    0.41
    POSITIVE LOGITS
     regresa
    0.54
     aldehyde
    0.50
     ημέ
    0.50
     मेंस
    0.50
     offerings
    0.49
     originalmente
    0.49
     కలిగి
    0.49
     posible
    0.48
     llamar
    0.48
     covariance
    0.48
    Activations Density 0.002%

    No Known Activations