© 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. 209260
    Prev
    Next
    INDEX
    Explanations

    release God, win their, use timestamps

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

    section titles

    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
    corsi
    0.49
    recommended
    0.48
     সাপ্তাহিক
    0.48
    ፈላ
    0.47
    torque
    0.47
    هُ
    0.47
    悴
    0.47
    ற்க
    0.46
    Indonesia
    0.45
    お客
    0.45
    POSITIVE LOGITS
     ñ
    0.55
     de
    0.55
    í
    0.52
    远远
    0.51
    )
    0.50
    phy
    0.47
    }
    0.46
    ät
    0.44
     destacar
    0.44
     destacó
    0.44
    Activations Density 0.000%

    No Known Activations