© 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. 83128
    Prev
    Next
    INDEX
    Explanations

    business proposals and workshops

    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
     postulated
    0.47
     UNHCR
    0.45
     рэгістрацыі
    0.43
    رافی
    0.43
    autoref
    0.41
    ך
    0.41
    껑
    0.41
     hypothes
    0.40
     스스로
    0.40
    ֽ
    0.40
    POSITIVE LOGITS
    BAR
    0.51
    DOM
    0.49
    SET
    0.45
    PER
    0.45
    pitch
    0.45
    BA
    0.45
    GROUP
    0.44
    GRO
    0.44
    top
    0.43
    RO
    0.42
    Activations Density 0.005%

    No Known Activations