© 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. 13091
    Prev
    Next
    INDEX
    Explanations

    amazing adjective intensifiers

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

    crucial disclaimer at the end

    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
    ":
    0.45
    :
    0.38
     "
    0.37
    あるいは
    0.37
     circa
    0.36
    或
    0.35
     gastronomic
    0.35
     или
    0.34
     ឬ
    0.34
     modestly
    0.34
    POSITIVE LOGITS
     sicuramente
    0.55
     بہت
    0.53
    pletely
    0.49
    <unused2117>
    0.48
     birçok
    0.48
     unbelievably
    0.48
     dems
    0.48
     assolutamente
    0.47
     굉장히
    0.46
     increíble
    0.46
    Activations Density 0.011%

    No Known Activations