© 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. 55452
    Prev
    Next
    INDEX
    Explanations

    airport fees for passengers

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

    foreign specific words

    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
    Ç
    0.55
    Tmp
    0.49
    Fe
    0.46
    tmp
    0.43
    Vice
    0.43
    Cuando
    0.43
    Gro
    0.42
    Č
    0.42
    T
    0.42
    JE
    0.41
    POSITIVE LOGITS
    ンジ
    0.45
    苾
    0.45
     என்பதற்கு
    0.44
     ու
    0.44
     aplic
    0.43
    กับ
    0.43
     কিংবা
    0.43
     развития
    0.42
     estánd
    0.42
     আচ
    0.42
    Activations Density 0.000%

    No Known Activations