© 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. 219662
    Prev
    Next
    INDEX
    Explanations

    because

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

    phrases with specific tokens like delta, reflection, safety

    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
     edgy
    0.43
     साकार
    0.43
     PHYSICAL
    0.41
     dehors
    0.40
     impermeable
    0.40
    notin
    0.40
     WATCH
    0.39
    ָ
    0.39
     পাশ্চাত্য
    0.39
     MARINE
    0.38
    POSITIVE LOGITS
    ки
    0.55
    뤽
    0.53
     çünkü
    0.49
    DataItem
    0.47
     protože
    0.47
    Asset
    0.46
    freund
    0.46
    republik
    0.46
     لأنه
    0.44
    워크
    0.44
    Activations Density 0.000%

    No Known Activations