© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2105
    Prev
    Next
    INDEX
    Explanations

    code comments followed by commands

    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_65k_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
    ،
    0.52
    :
    0.45
    ।
    0.38
    、
    0.36
    。
    0.35
    ・
    0.35
    ۔
    0.35
    ፡
    0.35
    ，
    0.34
    ﻥ
    0.34
    POSITIVE LOGITS
    t
    0.58
    w
    0.55
    b
    0.52
    ok
    0.46
    a
    0.46
    to
    0.45
    as
    0.44
    v
    0.44
    h
    0.43
    us
    0.43
    Activations Density 4.242%

    No Known Activations