© 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. 126383
    Prev
    Next
    INDEX
    Explanations

    social media, local business, technology

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

    inherently has, that goes

    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
    Investigators
    0.53
    Analysts
    0.50
    iodate
    0.49
    vous
    0.48
    એ
    0.48
    öner
    0.47
     cerevisiae
    0.47
    owę
    0.47
    Highlighted
    0.47
     months
    0.47
    POSITIVE LOGITS
    ლო
    0.48
     forne
    0.44
    ానిక
    0.43
     사용
    0.43
    Hozz
    0.42
     admon
    0.42
    擅
    0.42
    埋
    0.41
     accion
    0.41
    尚
    0.41
    Activations Density 0.000%

    No Known Activations