© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45605
    Prev
    Next
    INDEX
    Explanations

    masculinity, premise, hyperspace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isn
    0.47
     It
    0.45
     Pue
    0.44
    Ο
    0.42
     doesn
    0.41
    溥
    0.41
     streamline
    0.41
     wasn
    0.40
     Constructor
    0.40
     LaTeX
    0.40
    POSITIVE LOGITS
     insecurity
    0.46
     uncertainty
    0.46
     sovereignty
    0.45
    hluk
    0.41
     amenazas
    0.40
    ؤ
    0.40
    脅
    0.40
     socio
    0.39
     batas
    0.39
     terrified
    0.39
    Activations Density 0.009%

    No Known Activations