© 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. 182538
    Prev
    Next
    INDEX
    Explanations

    was reported

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

    units or rates of change

    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
     accret
    0.50
     but
    0.46
    setminus
    0.44
    Combination
    0.43
    acceptable
    0.43
    କ
    0.42
     ছাড়াই
    0.42
    دون
    0.42
    چ
    0.42
    ışt
    0.41
    POSITIVE LOGITS
     póź
    0.49
     nyní
    0.48
     sosok
    0.48
     දැන්
    0.48
     także
    0.46
     uname
    0.46
     myös
    0.45
     visage
    0.45
     yawning
    0.45
     rosto
    0.44
    Activations Density 0.001%

    No Known Activations