© 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. 237964
    Prev
    Next
    INDEX
    Explanations

    welcoming friends and activities

    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
    Char
    0.48
     DJ
    0.48
     D
    0.46
    OK
    0.46
    Bar
    0.46
     Jie
    0.46
     Ses
    0.46
    ар
    0.45
    </strong>
    0.44
     =\
    0.42
    POSITIVE LOGITS
     সাধন
    0.58
    簹
    0.55
     కారణంగా
    0.52
     friendliness
    0.51
     అనుమ
    0.50
     شدن
    0.50
    deprecation
    0.50
    conversation
    0.49
     collusion
    0.49
    quanto
    0.49
    Activations Density 0.001%

    No Known Activations