© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75130
    Prev
    Next
    INDEX
    Explanations

    HR process and optional details

    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
    ле
    0.55
     processi
    0.49
     immigrant
    0.48
    ваны
    0.47
    ще
    0.46
     Ро
    0.46
    х
    0.45
     annihil
    0.45
     mobili
    0.45
     shutdowns
    0.45
    POSITIVE LOGITS
    n
    0.55
    lN
    0.51
    )$$
    0.50
     απα
    0.48
    <0x11>
    0.45
     유명
    0.44
    toire
    0.43
    tilde
    0.43
    ฑ
    0.43
    nA
    0.43
    Activations Density 0.010%

    No Known Activations