© 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. 164898
    Prev
    Next
    INDEX
    Explanations

    storyteller witty laugh

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

    False Positive, Ephemeral, Panic

    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
     紙
    0.51
     Suddenly
    0.49
     塩
    0.46
    opot
    0.46
    Hydrochloride
    0.46
    ular
    0.46
     Mild
    0.46
     광고
    0.45
     Казах
    0.45
    ToServer
    0.45
    POSITIVE LOGITS
     witty
    0.49
     رہ
    0.46
    ឪ
    0.44
     storyteller
    0.44
    جل
    0.43
     laugh
    0.42
     Reve
    0.42
     revoked
    0.42
     fairytale
    0.41
     charted
    0.41
    Activations Density 0.000%

    No Known Activations