© 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. 216456
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

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

    urban legends, folklore, myths, specific names

    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
    霝
    0.46
     detach
    0.45
     even
    0.44
     interactions
    0.44
     prefer
    0.43
     জৈ
    0.43
     onboarding
    0.43
     biodiversity
    0.43
     mới
    0.43
     detal
    0.42
    POSITIVE LOGITS
    timevals
    0.49
    ੩
    0.48
    હુ
    0.45
     Ako
    0.44
    igrams
    0.43
    showinfo
    0.42
    Unt
    0.41
    त्रे
    0.40
     TouchUtils
    0.40
    otiti
    0.40
    Activations Density 0.000%

    No Known Activations