© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 39899
    Prev
    Next
    INDEX
    Explanations

    seeing or witnessing

    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_53_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
     talk
    0.46
     ask
    0.43
    Ask
    0.43
     Ask
    0.42
     claiming
    0.41
     admit
    0.41
     Exercise
    0.41
    思
    0.40
     Talking
    0.40
     придума
    0.40
    POSITIVE LOGITS
     privy
    0.73
     eaves
    0.65
     witness
    0.62
    Witness
    0.61
     overhear
    0.56
     glimpse
    0.55
     glimpses
    0.55
     witnesses
    0.54
    witness
    0.54
     glimps
    0.53
    Activations Density 0.008%

    No Known Activations