© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11568
    Prev
    Next
    INDEX
    Explanations

    present needs without future

    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_13_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
    ン
    1.51
    ة
    1.09
    น
    1.08
     BAND
    1.05
     bande
    1.05
     Band
    1.04
     adelante
    1.03
     band
    1.01
    i
    1.01
    Band
    1.00
    POSITIVE LOGITS
    akkhati
    1.34
    ensely
    1.27
     expenditure
    1.23
     evaporation
    1.21
    ảnh
    1.21
     retros
    1.21
     lecturing
    1.20
     stressful
    1.20
     regression
    1.16
    sns
    1.15
    Activations Density 0.000%

    No Known Activations