© 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. 216545
    Prev
    Next
    INDEX
    Explanations

    first other languages

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

    Immediate actions

    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
    lach
    0.48
     quibusdam
    0.44
     accidents
    0.42
     отме
    0.41
    酱
    0.41
     capaces
    0.40
     capables
    0.40
     אבל
    0.40
    laus
    0.40
     不过
    0.40
    POSITIVE LOGITS
     allere
    0.46
     फर्स्ट
    0.45
     первое
    0.44
     erstes
    0.43
     −
    0.43
     Sixth
    0.43
     डिस
    0.43
    Detail
    0.42
    Transition
    0.42
     eerste
    0.42
    Activations Density 0.001%

    No Known Activations