© 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. 46748
    Prev
    Next
    INDEX
    Explanations

    may have

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

    creation, existence, or destruction

    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
    众人
    0.53
     помещения
    0.49
    掩
    0.47
     sosyal
    0.46
     nevoia
    0.46
     Hoje
    0.46
    ariye
    0.45
     désir
    0.45
     connecté
    0.45
     pdelay
    0.44
    POSITIVE LOGITS
    ally
    0.55
    revision
    0.48
    research
    0.46
    s
    0.46
    asp
    0.45
    ref
    0.45
     slightly
    0.45
    trans
    0.44
    region
    0.43
    methods
    0.42
    Activations Density 0.000%

    No Known Activations