© 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. 98802
    Prev
    Next
    INDEX
    Explanations

    phrases after "to"

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

    fantastic questions and enthusiastic replies

    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
     OJ
    0.45
     that
    0.45
    െ
    0.44
     positional
    0.43
     establishes
    0.43
     //@
    0.42
    كان
    0.42
    充
    0.42
     amounting
    0.41
     internally
    0.41
    POSITIVE LOGITS
     विस्तारित
    0.52
     नीचे
    0.48
     मौसम
    0.47
    hitting
    0.47
    ियत
    0.47
    ullah
    0.46
     delicioso
    0.45
     मोह
    0.43
    kul
    0.43
    skom
    0.43
    Activations Density 0.000%

    No Known Activations