© 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. 45888
    Prev
    Next
    INDEX
    Explanations

    member of affiliation

    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
     হরত
    0.49
    狽
    0.44
     Browne
    0.40
    ㄳ
    0.40
    ▆
    0.40
     mortg
    0.40
     outre
    0.40
    ॥
    0.39
    子公司
    0.38
     hangat
    0.38
    POSITIVE LOGITS
    we
    0.44
     panes
    0.44
    ifizierung
    0.43
     clarity
    0.42
    ash
    0.42
    ih
    0.42
    ito
    0.41
     ejaculation
    0.41
    ifix
    0.40
    Expert
    0.40
    Activations Density 0.006%

    No Known Activations