© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1897
    Prev
    Next
    INDEX
    Explanations

    existential and life experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    Č
    2.71
    haba
    2.62
    .".,
    2.58
    ínsula
    2.57
    yyati
    2.55
     mắn
    2.54
    semanticweb
    2.53
    Б
    2.53
    SIX
    2.52
    કિસ્તા
    2.51
    POSITIVE LOGITS
     (‘
    2.34
     traps
    2.22
     din
    2.20
    بیداری
    2.17
    }}^{(
    2.13
    рна
    2.13
    otri
    2.13
    ropol
    2.12
    糰
    2.11
    fl
    2.07
    Activations Density 0.236%

    No Known Activations