© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221761
    Prev
    Next
    INDEX
    Explanations

    twisted, mutual, friends

    np_acts-logits-general · gemini-2.5-flash-lite

    critique leveled against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dishon
    0.52
     ಮತ್ತು
    0.50
     &/
    0.45
     partic
    0.45
     aggress
    0.44
     மற்றும்
    0.44
     wast
    0.44
    dasarkan
    0.43
     discriminatory
    0.43
     activates
    0.43
    POSITIVE LOGITS
     unaltered
    0.45
    乸
    0.44
     ஒரே
    0.42
    单个
    0.42
    }}^{*}
    0.41
    јединачна
    0.41
    イレ
    0.41
    một
    0.41
    烹
    0.40
    зи
    0.40
    Activations Density 0.005%

    No Known Activations