© 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. 232794
    Prev
    Next
    INDEX
    Explanations

    blissful states

    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
    过
    0.59
    過
    0.53
    eszcze
    0.51
     bauen
    0.50
     forgiven
    0.49
    çado
    0.49
    纸
    0.49
    Prov
    0.48
    叄
    0.48
    ஒரு
    0.47
    POSITIVE LOGITS
     ita
    0.47
     keadaan
    0.46
     Athlete
    0.45
     it
    0.45
    とその
    0.44
     atletas
    0.43
     its
    0.43
     desliz
    0.43
     situa
    0.42
     bhavanti
    0.42
    Activations Density 0.000%

    No Known Activations