© 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. 66997
    Prev
    Next
    INDEX
    Explanations

    time to grows

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

    evidence of

    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
     soybeans
    0.49
     steampunk
    0.46
    ЕД
    0.45
     AREA
    0.45
    ἷ
    0.44
     '{}
    0.44
     FRIED
    0.44
    仙
    0.43
    ल्ड
    0.43
     FEST
    0.42
    POSITIVE LOGITS
    resposta
    0.59
    ske
    0.53
    voor
    0.52
    pathy
    0.52
    govor
    0.51
    zeichnung
    0.49
    feeding
    0.48
    sense
    0.47
    faq
    0.47
     වා
    0.47
    Activations Density 0.001%

    No Known Activations