© 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. 81167
    Prev
    Next
    INDEX
    Explanations

    determiner possessive pronoun common noun

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

    negation and contrast

    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
    Liqu
    0.47
     灯
    0.47
    alk
    0.46
    Coat
    0.46
    ക്കാർ
    0.44
    utherford
    0.44
    irat
    0.44
    Lantern
    0.43
    irar
    0.43
    Lew
    0.43
    POSITIVE LOGITS
     próxima
    0.56
     automóviles
    0.51
     adecu
    0.49
     complejo
    0.49
     intérêts
    0.49
     acier
    0.48
    ྛ
    0.48
     envío
    0.47
    数据
    0.47
     možné
    0.47
    Activations Density 0.000%

    No Known Activations