© 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. 130733
    Prev
    Next
    INDEX
    Explanations

    following words after common words

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

    Hub Sites, Hiking Shoes, hysteresis threshold

    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
    ാമ
    0.48
    спо
    0.44
    мб
    0.44
     principled
    0.43
    ቸ
    0.43
    ін
    0.42
     inconvén
    0.42
     pdelay
    0.42
    tochy
    0.42
    ंगिक
    0.42
    POSITIVE LOGITS
     feria
    0.49
    在她
    0.47
     Feria
    0.46
     serendip
    0.46
    o
    0.46
     Serpent
    0.46
    லைப்
    0.46
     Espí
    0.44
    லைக்
    0.43
     Sonata
    0.42
    Activations Density 0.000%

    No Known Activations