© 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. 216593
    Prev
    Next
    INDEX
    Explanations

    deployment and instructions

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

    technical terms and common phrases

    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
    ဘူး
    0.49
    ǒu
    0.49
     Particle
    0.48
    ﺕ
    0.46
    𝓌
    0.46
     Chuck
    0.45
     Sonu
    0.45
    𝓉
    0.45
     jestem
    0.44
    ସ
    0.44
    POSITIVE LOGITS
    alia
    0.48
    ile
    0.43
     transacción
    0.41
    ARIA
    0.41
    radas
    0.40
     expedient
    0.40
     ци
    0.40
     финансо
    0.40
    rith
    0.39
    imate
    0.39
    Activations Density 0.000%

    No Known Activations