© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117441
    Prev
    Next
    INDEX
    Explanations

    rather deeply, instead

    np_acts-logits-general · gemini-2.5-flash-lite

    mood, states, and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ף
    0.55
    過了
    0.46
    ק
    0.46
    كره
    0.46
    avanja
    0.45
    خلي
    0.45
    斯科
    0.45
    בר
    0.45
    രാണ്
    0.45
    索
    0.44
    POSITIVE LOGITS
     rather
    0.53
     بجائے
    0.53
     mood
    0.51
     instead
    0.47
     nerves
    0.47
     medicines
    0.46
     soothing
    0.45
     médiocrement
    0.45
     বরং
    0.45
     moods
    0.45
    Activations Density 0.000%

    No Known Activations