© 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. 55989
    Prev
    Next
    INDEX
    Explanations

    inquiring about reasons

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

    religions & geopolitical conflicts

    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
     Ã
    0.42
     quadruple
    0.42
     sudut
    0.40
    数は
    0.40
     està
    0.40
    hl
    0.39
    Signin
    0.38
     setup
    0.38
     éste
    0.38
     keenly
    0.38
    POSITIVE LOGITS
    पूर्वी
    0.49
     intruders
    0.48
     ファン
    0.48
    ნიშვნელ
    0.47
     保護
    0.47
    𝗍
    0.45
     chatbots
    0.45
     gobl
    0.44
    غاز
    0.44
     intrusions
    0.43
    Activations Density 0.000%

    No Known Activations