© 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. 34288
    Prev
    Next
    INDEX
    Explanations

    Buying and reviewing experiences

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

    don't feel, don't try, don't let

    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
    Abstraction
    0.28
     Entonces
    0.26
     aforementioned
    0.26
    》（
    0.26
    .[
    0.25
    uminescent
    0.25
     oeuvre
    0.25
    <sub>
    0.24
     [(
    0.24
     యొక్క
    0.24
    POSITIVE LOGITS
     fintech
    0.32
     BTW
    0.31
     snd
    0.31
     tiktok
    0.30
    ಲೂ
    0.30
     २०२
    0.29
     Fintech
    0.29
     ThinQ
    0.29
     Biden
    0.29
    createdAt
    0.29
    Activations Density 0.010%

    No Known Activations