© 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. 169148
    Prev
    Next
    INDEX
    Explanations

    following academic or professional terms

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

    risks everything, incoming call

    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
    шие
    0.52
    განიზ
    0.50
     plaid
    0.46
    粡
    0.46
     chemokine
    0.44
     createState
    0.44
    鏘
    0.44
    ين
    0.43
     pertain
    0.43
     montant
    0.43
    POSITIVE LOGITS
    ayn
    0.52
    gående
    0.47
    RecordPtr
    0.46
     starten
    0.46
    äne
    0.46
    }.$$
    0.45
     ifelse
    0.44
    Ouest
    0.44
    IfNeeded
    0.44
    Recorder
    0.44
    Activations Density 0.000%

    No Known Activations