© 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. 122203
    Prev
    Next
    INDEX
    Explanations

    recommended conversion specialists

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

    pronoun avoidance, spending time, website usage

    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
    ij
    0.46
    Secrets
    0.46
    Inj
    0.46
    او
    0.46
    Proj
    0.45
    JH
    0.44
    Neurons
    0.44
    א
    0.44
    arten
    0.43
    ولوج
    0.43
    POSITIVE LOGITS
     IRB
    0.54
     audiencia
    0.53
     XGB
    0.53
     OLED
    0.52
     Accenture
    0.52
     Acura
    0.52
     batería
    0.50
     RFID
    0.50
     baterías
    0.49
     лен
    0.49
    Activations Density 0.001%

    No Known Activations