© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58581
    Prev
    Next
    INDEX
    Explanations

    phase transitions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xadrez
    -0.90
    ᾰ
    -0.87
    きれい
    -0.85
    çs
    -0.85
     généralement
    -0.85
    adorable
    -0.84
     relâche
    -0.84
    ДС
    -0.84
    playable
    -0.81
    ranging
    -0.81
    POSITIVE LOGITS
     phases
    1.38
     phase
    1.35
     states
    1.26
     state
    1.14
     solution
    1.13
    like
    1.02
     at
    1.00
     in
    0.98
     problem
    0.98
     picture
    0.95
    Activations Density 0.125%

    No Known Activations