© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4312
    Prev
    Next
    INDEX
    Explanations

    double

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     Henson
    1.40
     Voss
    1.24
     Puppet
    1.22
     MNR
    1.19
    :<
    1.15
     NOC
    1.15
     Patrol
    1.15
     sequencer
    1.13
    Prog
    1.12
    !:
    1.12
    POSITIVE LOGITS
     Double
    2.38
    Double
    2.35
     double
    2.34
    double
    2.31
     DOUBLE
    2.26
     triple
    2.19
     doubles
    2.15
     Doubles
    2.15
    DOUBLE
    2.10
     quadruple
    2.05
    Activations Density 0.029%

    No Known Activations