© 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. 212989
    Prev
    Next
    INDEX
    Explanations

    costs and deals

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

    cost savings and population impacts

    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
     засе
    0.54
    Ή
    0.49
    པ
    0.48
     молодой
    0.47
    结果
    0.46
    Ң
    0.46
    結局
    0.46
    NoStop
    0.46
    쟁
    0.46
    면서
    0.46
    POSITIVE LOGITS
     martial
    0.60
     motor
    0.51
     devastation
    0.50
     prehistoric
    0.50
     fortification
    0.50
     surviv
    0.47
     anarchy
    0.47
     inj
    0.47
     majesty
    0.46
     tycoon
    0.46
    Activations Density 0.001%

    No Known Activations