© 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. 137865
    Prev
    Next
    INDEX
    Explanations

    laws and attain

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

    hit ... model

    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
     personally
    0.50
    OD
    0.48
     inco
    0.47
    s
    0.47
    TER
    0.46
     kappa
    0.46
     אח
    0.46
     dabb
    0.46
     different
    0.46
     incoherent
    0.46
    POSITIVE LOGITS
     রিটার
    0.51
    氫
    0.50
    氬
    0.50
    ítě
    0.47
    諾
    0.46
     Logistic
    0.45
    靔
    0.45
     logros
    0.45
    㖩
    0.44
     आविष्कार
    0.44
    Activations Density 0.001%

    No Known Activations