© 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-65K
    7. 54926
    Prev
    Next
    INDEX
    Explanations

    recovered 'flying disc'

    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_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
    angles
    0.48
    $<
    0.48
    working
    0.45
    else
    0.44
     bekerja
    0.43
    සු
    0.41
    utiliser
    0.41
    directions
    0.41
    sunami
    0.41
    ben
    0.40
    POSITIVE LOGITS
    ㈱
    0.42
     mā
    0.41
     wych
    0.40
     asset
    0.39
     nikdy
    0.38
     spirit
    0.38
     creation
    0.38
     Morrow
    0.38
    씀
    0.38
     	i
    0.38
    Activations Density 0.000%

    No Known Activations