© 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. 105480
    Prev
    Next
    INDEX
    Explanations

    comparisons and approximations

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

    versions and upgrades

    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
    ：
    0.50
    ۝
    0.49
    ola
    0.46
     コー
    0.46
     Configuration
    0.45
    ⚠
    0.45
    m
    0.45
     clara
    0.44
    ః
    0.44
    ﻭ
    0.44
    POSITIVE LOGITS
     তুলনায়
    0.46
     idealized
    0.46
     предела
    0.42
     approximations
    0.42
     ansatz
    0.42
    版本的
    0.41
    关系的
    0.41
     तुलना
    0.41
     approximates
    0.41
    するという
    0.41
    Activations Density 0.001%

    No Known Activations