© 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. 59598
    Prev
    Next
    INDEX
    Explanations

    spreading gossip and rumors

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

    telling gossip and rumors

    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
     اسلح
    0.49
     liber
    0.48
     battling
    0.46
     éduc
    0.45
    拒
    0.43
     اتباع
    0.43
     weapons
    0.43
     serene
    0.43
     liberating
    0.43
     درخواست
    0.42
    POSITIVE LOGITS
     gossip
    1.67
     goss
    1.45
     Gossip
    1.41
    噂
    1.18
     rumor
    1.17
     rumors
    1.16
     rumour
    1.16
     rumours
    1.12
     hearsay
    1.11
     rumores
    1.09
    Activations Density 0.041%

    No Known Activations