© 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. 137805
    Prev
    Next
    INDEX
    Explanations

    satellite TV

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

    If so, then

    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
    ariest
    0.52
     sacraments
    0.52
     (<
    0.51
     vilken
    0.49
     narratives
    0.49
     vilka
    0.48
     Estat
    0.48
     письмен
    0.47
     semblables
    0.47
     якому
    0.47
    POSITIVE LOGITS
    //}
    0.46
     Applying
    0.44
    Vx
    0.43
    ెం
    0.43
    חות
    0.42
    remove
    0.41
     Flughafen
    0.41
     добавить
    0.41
     aplicar
    0.41
     করতো
    0.41
    Activations Density 0.001%

    No Known Activations