© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    crisis lifeline

    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
    𝚑
    3.03
    𝚖
    2.86
    ᱣ
    2.82
    𝚍
    2.81
    ᱶ
    2.75
    ⊇
    2.71
    Selon
    2.69
    ldecode
    2.67
    ټر
    2.61
    şil
    2.61
    POSITIVE LOGITS
    s
    3.45
     else
    2.78
    Else
    2.60
    som
    2.56
    song
    2.50
    nnnn
    2.42
    ような
    2.38
    squ
    2.35
     Else
    2.35
    toHaveBeenCalled
    2.28
    Activations Density 0.170%

    No Known Activations