© 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. 196279
    Prev
    Next
    INDEX
    Explanations

    essay, beispiel

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

    phrases introducing a concept

    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
    İ
    0.61
    Paw
    0.57
    Minister
    0.51
    Political
    0.49
    Ě
    0.47
    Boo
    0.47
    Ə
    0.46
    D
    0.46
    inth
    0.46
     bites
    0.46
    POSITIVE LOGITS
     નવી
    0.47
     તેણી
    0.47
     ચ
    0.47
     CONTINUE
    0.47
    сти
    0.45
    >©
    0.45
     dvara
    0.45
     ઘરે
    0.44
     ダブル
    0.44
    jir
    0.44
    Activations Density 0.001%

    No Known Activations