© 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. 23950
    Prev
    Next
    INDEX
    Explanations

    grounding stone, Swiss National

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

    navigation and queries

    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
    𝟯
    0.46
     critica
    0.46
    έχ
    0.45
    sair
    0.45
     posición
    0.43
    =".$
    0.43
     francês
    0.42
    氫
    0.42
     gespielt
    0.42
     強
    0.42
    POSITIVE LOGITS
     दाएं
    0.51
    erical
    0.48
     पता
    0.45
     Query
    0.44
    ных
    0.44
     Shifts
    0.44
    legraph
    0.43
     Uncertainty
    0.43
     Twelfth
    0.43
     leaps
    0.43
    Activations Density 0.000%

    No Known Activations