© 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. 31914
    Prev
    Next
    INDEX
    Explanations

    has always, feel a

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

    year, term, thresholds, goals, party, Identity, Panic

    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
     tradizionale
    0.47
    JUNE
    0.47
     هفته
    0.44
    容
    0.44
    uing
    0.43
     раху
    0.43
     REGIUNI
    0.43
    জ
    0.43
    瀝
    0.43
     فر
    0.42
    POSITIVE LOGITS
    𒊭
    0.55
    emporary
    0.52
    arist
    0.50
    ashe
    0.50
    ari
    0.50
    ast
    0.47
    tuk
    0.47
    ishan
    0.46
     poset
    0.46
    aric
    0.45
    Activations Density 0.000%

    No Known Activations