© 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. 198317
    Prev
    Next
    INDEX
    Explanations

    late Capt

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

    specialization, bonus, induced psychosis, created

    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
    es
    0.54
    un
    0.54
    :
    0.54
    ub
    0.48
    ıyorum
    0.47
    istic
    0.47
     Untitled
    0.46
     APPLY
    0.44
    more
    0.44
    mutual
    0.44
    POSITIVE LOGITS
     králov
    0.51
     risked
    0.46
     cirrh
    0.45
     meriye
    0.44
    រប
    0.44
    ITATE
    0.44
    ᖕ
    0.43
     larc
    0.43
     ಹೃ
    0.42
     comerciais
    0.42
    Activations Density 0.000%

    No Known Activations