© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    unstated feelings and unintended effects

    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
     stay
    1.68
     stock
    1.65
     remain
    1.61
    itarian
    1.57
    ty
    1.50
     visitors
    1.45
    에
    1.42
    ’;
    1.41
    ম্ভ
    1.40
     remains
    1.39
    POSITIVE LOGITS
    ∮
    2.27
    ◇
    2.19
    стояния
    2.17
    "^
    2.11
    ಹಾಸ
    2.11
    ₚ
    2.09
    𒀸
    2.03
     '^
    2.02
    ynchus
    2.02
    riendo
    2.02
    Activations Density 0.052%

    No Known Activations