© 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. 127188
    Prev
    Next
    INDEX
    Explanations

    claim, designed, rules, felt familiar

    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
    三個
    0.52
    Intern
    0.47
    CEO
    0.46
     Business
    0.46
    Gateway
    0.46
    閤
    0.45
    داخل
    0.45
    合金
    0.45
    Business
    0.45
    Investment
    0.45
    POSITIVE LOGITS
     evitare
    0.50
     occlusion
    0.50
     dakkh
    0.50
     evit
    0.47
     unclear
    0.46
     this
    0.45
     probed
    0.45
     nelle
    0.45
     তাই
    0.45
     ].
    0.45
    Activations Density 0.007%

    No Known Activations