© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12558
    Prev
    Next
    INDEX
    Explanations

    years followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ាល
    0.42
    ވަ
    0.39
    ﻭ
    0.39
    نت
    0.38
     annen
    0.37
    ματο
    0.37
    ود
    0.37
    手間
    0.36
     ovipares
    0.36
     entour
    0.36
    POSITIVE LOGITS
    chin
    0.50
    ī
    0.45
    ibb
    0.43
    onga
    0.41
    enda
    0.40
    ik
    0.40
    liga
    0.40
    imli
    0.39
    ád
    0.38
    ligt
    0.38
    Activations Density 0.041%

    No Known Activations