© 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. 12458
    Prev
    Next
    INDEX
    Explanations

    awesome, fantastic, increase

    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
    ారు
    1.68
    htra
    1.53
    (&
    1.50
    𝚑
    1.50
    
    1.46
    öl
    1.45
    ("&
    1.45
    ůj
    1.43
    𝚐
    1.42
     solides
    1.40
    POSITIVE LOGITS
    s
    1.93
    ᵏ
    1.90
    ریک
    1.87
    दू
    1.83
    mits
    1.83
    rins
    1.76
    NUMX
    1.73
    rification
    1.73
    elines
    1.71
    rish
    1.71
    Activations Density 0.000%

    No Known Activations