© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 199821
    Prev
    Next
    INDEX
    Explanations

    family members or other groups

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

    Yo, check the mic, one two

    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
     වැඩි
    0.64
     albi
    0.58
     മ
    0.50
     து
    0.50
     abrió
    0.50
     மில்லியன்
    0.50
     เว
    0.49
    वेयर
    0.48
     этими
    0.48
     metabolized
    0.47
    POSITIVE LOGITS
    s
    0.57
     Financial
    0.46
    .
    0.44
    Soft
    0.44
    Browser
    0.43
     WordPress
    0.42
    er
    0.42
    ار
    0.41
    Inter
    0.41
    >.
    0.41
    Activations Density 0.001%

    No Known Activations