© 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. 110562
    Prev
    Next
    INDEX
    Explanations

    formal and informal explanations

    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
    atched
    0.47
    rivial
    0.46
     비교
    0.44
     ଅ
    0.44
    agerie
    0.43
    apparently
    0.43
    hed
    0.42
    matched
    0.42
    έ
    0.41
    utter
    0.41
    POSITIVE LOGITS
     escalate
    0.51
     peoples
    0.50
     használ
    0.49
     cuidados
    0.48
     digits
    0.46
     nuevas
    0.46
     Peoples
    0.46
     administ
    0.45
     nuevos
    0.45
    ز
    0.45
    Activations Density 0.018%

    No Known Activations