© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 119957
    Prev
    Next
    INDEX
    Explanations

    Prefixes followed by specific continuations

    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_16_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
    2
    1.15
    ﻞ
    0.78
    Reactor
    0.77
    ﻓ
    0.77
    לו
    0.76
    ﻟ
    0.76
    타
    0.75
     ilość
    0.75
    在
    0.73
    ซ์
    0.73
    POSITIVE LOGITS
    m
    1.45
    b
    1.27
    v
    1.21
    t
    1.20
    k
    1.20
    j
    1.15
    d
    1.14
    h
    1.13
    s
    1.10
    g
    1.08
    Activations Density 0.000%

    No Known Activations