© 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. 132796
    Prev
    Next
    INDEX
    Explanations

    commitment period

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

    technical planning and project elements

    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
    ｼ
    0.44
     hearty
    0.43
    કરી
    0.42
     uguale
    0.42
    PY
    0.42
     ristor
    0.42
    PAR
    0.42
    STR
    0.41
    Theorem
    0.41
    ܫ
    0.41
    POSITIVE LOGITS
     কারও
    0.47
     الوضع
    0.47
    émi
    0.46
    údo
    0.44
    getBlueTeam
    0.44
     அவரது
    0.44
     Phật
    0.44
     Développement
    0.44
     அவர்களுக்கு
    0.42
     එ
    0.42
    Activations Density 0.001%

    No Known Activations