© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6154
    Prev
    Next
    INDEX
    Explanations

    Mount, historic, May, Frank

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

    SAMHSA National Helpline

    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_53_width_65k_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
     positiva
    0.38
    Diagn
    0.38
    딪
    0.38
    ToSend
    0.37
     Improvement
    0.37
    lection
    0.37
    diagn
    0.37
    ニ
    0.37
    긍
    0.37
     Positive
    0.37
    POSITIVE LOGITS
     Samuel
    0.45
     particulars
    0.44
     seamen
    0.44
     William
    0.42
     extending
    0.42
     Beg
    0.41
     Robert
    0.40
    Samuel
    0.40
     Charles
    0.40
     Bock
    0.40
    Activations Density 0.008%

    No Known Activations