© 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. 40038
    Prev
    Next
    INDEX
    Explanations

    Temple of

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

    thinking and seeming

    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
    ...
    0.50
     F
    0.49
    …
    0.49
     E
    0.48
     pioneer
    0.48
     mage
    0.47
     tasked
    0.46
    BE
    0.44
    .?
    0.44
     pioneers
    0.44
    POSITIVE LOGITS
     প্রাণে
    0.53
     परस्मैपदी
    0.52
     lézards
    0.51
    㐄
    0.51
    小さい
    0.50
    ποί
    0.50
    ômios
    0.49
     সম্মিল
    0.49
     রাখ
    0.48
     méridionale
    0.47
    Activations Density 0.000%

    No Known Activations