© 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. 51488
    Prev
    Next
    INDEX
    Explanations

    sequences after keywords

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

    vulnerability, percentage, equation, restrained, traditionally, describe, management

    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
    bikes
    0.51
    🐕
    0.47
    Mga
    0.44
    Topics
    0.42
    Groups
    0.41
     europeo
    0.41
     waterways
    0.40
    Published
    0.40
    種類
    0.40
     phosphates
    0.40
    POSITIVE LOGITS
     술
    0.49
     경우는
    0.44
    十章
    0.44
     경우에는
    0.43
     сете
    0.42
     Shelton
    0.40
    ৃত
    0.39
    ogun
    0.39
     감독
    0.38
     هي
    0.38
    Activations Density 0.000%

    No Known Activations